© 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 · 9647 ｜ Neuronpedia

Home
Gemma-2-27B
22-GEMMASCOPE-RES-131K
9647

INDEX

Explanations

phone numbers

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

泐

-1.44

 moelle

-1.36

 exigir

-1.29

 resistir

-1.28

 souha

-1.27

 étranger

-1.24

睒

-1.24

 prépare

-1.22

duled

-1.21

essoas

-1.20

POSITIVE LOGITS

1.40

1.32

</b>

1.15

ing

1.09

AFFIRMED

1.05

ременно

1.01

1.01

Incoming

0.99

0.98

ты

0.96

Activations Density 0.002%

No Known Activations