© 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-3-1B · 13-GEMMASCOPE-2-RES-16K · 5247 ｜ Neuronpedia

Home
Gemma-3-1B
13-GEMMASCOPE-2-RES-16K
5247

INDEX

Explanations

mistakes and errors

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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

Leb

1.08

 Bedür

1.07

 чувства

0.94

唤

0.93

 الأح

0.92

élite

0.91

urg

0.91

uline

0.89

兴趣

0.88

津

0.88

POSITIVE LOGITS

 errors

1.53

 Errors

1.50

 error

1.50

Errors

1.47

 Error

1.45

 ERROR

1.44

 glitches

1.43

 erros

1.40

 mistakes

1.38

 erreurs

1.37

Activations Density 0.359%

No Known Activations