© 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 · 22-GEMMASCOPE-2-RES-16K · 8 ｜ Neuronpedia

Home
Gemma-3-1B
22-GEMMASCOPE-2-RES-16K
8

INDEX

Explanations

words followed by punctuation

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_22_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

দিগকে

1.27

"]="

1.23

કમાં

1.22

()}')

1.19

/>}/>

1.19

 DCHECK

1.19

ಳಿಗೆ

1.19

bindingNavigator

1.18

ಭವ

1.17

 />}/>

1.15

POSITIVE LOGITS

5.59

،

4.74

,<

4.19

,(

4.08

4.04

,,

4.01

，

3.99

,*

3.96

,[

3.94

、

3.91

Activations Density 22.390%

No Known Activations