© 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 · 14105 ｜ Neuronpedia

Home
Gemma-3-1B
7-GEMMASCOPE-2-RES-16K
14105

INDEX

Explanations

independent

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

Â

2.65

aln

2.45

2.40

TRA

2.35

থিত

2.32

ائط

2.31

ം

2.29

TUR

2.20

soever

2.17

 велико

2.14

POSITIVE LOGITS

semer

3.64

ところで

2.91

sem

2.79

ዘጋ

2.78

 eyed

2.68

ன்ற

2.66

cios

2.66

 mener

2.60

紝

2.60

stelling

2.59

Activations Density 0.024%

No Known Activations