Gemma 3
Google DeepMind — Gemma
rich detail 22 method fields published
Evaluation
Representational harms evaluation (text-to-text and image-to-text)
evaluation of text-to-text and image-to-text prompts covering safety policies including bias, stereotyping, and harmful associations or inaccuracies; results reported on minimal policy violations and improvements on ungrounded inferences
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.