© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-3-1B · 7-GEMMASCOPE-2-RES-16K · 304 ｜ Neuronpedia

Home
Gemma-3-1B
7-GEMMASCOPE-2-RES-16K
304

INDEX

Explanations

how, what, modern China

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_7_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

žené

1.78

pine

1.67

 pide

1.60

奈

1.60

 taka

1.59

olved

1.57

iamen

1.57

 metà

1.57

yat

1.56

PORTS

1.55

POSITIVE LOGITS

ǌ

1.78

hæng

1.67

Ing

1.65

ing

1.63

oing

1.63

eing

1.61

{%

1.59

 बाजार

1.56

addSprite

1.56

eae

1.54

Activations Density 0.000%

No Known Activations