© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 102439 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
102439

INDEX

Explanations

specific proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 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

 saranno

-2.20

饜

-2.09

茈

-2.05

㩒

-2.02

揷

-1.98

 dacă

-1.96

 vengono

-1.96

eſ

-1.94

 verranno

-1.91

釹

-1.91

POSITIVE LOGITS

2.11

优秀

1.94

ৄ

1.91

 AWESOME

1.89

‘

1.86

 Could

1.84

 Either

1.81

1.80

 cursory

1.80

有机

1.77

Activations Density 0.020%

No Known Activations