© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GEMMA-3-27B · 31-GEMMASCOPE-2-RES-262K · 185659 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
185659

INDEX

Explanations

quality of life

np_acts-logits-general · gemini-2.5-flash-lite

D&D

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

 mať

0.59

措置

0.52

杝

0.48

 বর্ষ

0.48

佢

0.48

 עם

0.47

 Subhanahu

0.47

 चालू

0.46

 दोहरा

0.46

颶

0.46

POSITIVE LOGITS

New

0.46

Ple

0.45

Ple

0.45

0.44

 Transforming

0.42

 transforming

0.41

Combined

0.41

raw

0.41

0.41

Low

0.40

Activations Density 0.001%

No Known Activations