© 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-3-12B · 41-GEMMASCOPE-2-RES-65K · 13491 ｜ Neuronpedia

Home
Gemma-3-12B
41-GEMMASCOPE-2-RES-65K
13491

INDEX

Explanations

mammal

np_max-act-logits · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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

Not in Any Lists

No Comments

Negative Logits

陋

0.55

Lu

0.54

ናት

0.52

orph

0.51

 orphan

0.51

Kac

0.51

Decorative

0.50

Koordin

0.50

ޅ

0.50

 decorative

0.49

POSITIVE LOGITS

 mamm

1.57

 mammoth

1.46

 Mammoth

1.38

 mast

1.23

mam

1.22

 Mamm

1.18

Mamm

1.13

mamm

1.12

 wool

1.11

 Mast

1.10

Activations Density 0.041%

No Known Activations