© 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 · 22-GEMMASCOPE-RES-131K · 27977 ｜ Neuronpedia

Home
Gemma-2-27B
22-GEMMASCOPE-RES-131K
27977

INDEX

Explanations

phone numbers and codes

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_22/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

moiselle

-1.38

"&

-1.36

quelles

-1.34

ksamkeit

-1.33

VertexAttrib

-1.31

()"

-1.30

----</

-1.28

*/

-1.28

sû

-1.27

 atriz

-1.27

POSITIVE LOGITS

1.42

1.27

1.18

1.13

 उन्ह

1.11

1.09

 kyse

1.09

During

1.08

Abit

1.06

Recap

1.05

Activations Density 0.003%

No Known Activations