© 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 · 7-GEMMASCOPE-2-RES-16K · 12207 ｜ Neuronpedia

Home
Gemma-3-1B
7-GEMMASCOPE-2-RES-16K
12207

INDEX

Explanations

must-see, must-do

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

𝕠

2.46

шня

2.28

狎

2.22

 separación

2.22

MULTIP

2.21

ጕ

2.21

揣

2.20

ല്ലാം

2.19

क्षकों

2.19

 cominci

2.18

POSITIVE LOGITS

ic

1.78

ئي

1.64

ver

1.59

ingly

1.58

’

1.56

epit

1.54

 appreciate

1.54

be

1.53

ெ

1.49

url

1.49

Activations Density 0.024%

No Known Activations