© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-3-27B-IT · 41-GEMMASCOPE-2-RES-262K · 653 ｜ Neuronpedia

Home
Gemma-3-27B-IT
41-GEMMASCOPE-2-RES-262K
653

INDEX

Explanations

fish and fish-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 മിക

0.56

 procé

0.54

ัติ

0.52

ૂર્ણ

0.51

 élytres

0.50

칡

0.50

 പ്രവർത്തന

0.49

 năng

0.48

andidates

0.48

ব্লিউ

0.48

POSITIVE LOGITS

 fish

2.23

 Fish

1.95

🐟

1.87

Fish

1.82

 fishes

1.78

鱼

1.77

魚

1.75

fish

1.73

 FISH

1.71

 pescado

1.65

Activations Density 0.025%

No Known Activations