© 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 · 127197 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
127197

INDEX

Explanations

http and https urls

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

’

-1.60

IALE

-1.52

 herida

-1.44

ientos

-1.43

不明白

-1.39

୩

-1.38

倣

-1.36

'].'

-1.34



-1.34

 filhos

-1.34

POSITIVE LOGITS

to

2.34

 direttore

1.48

などなど

1.48

 produttore

1.48

神

1.44

 sowohl

1.43

 after

1.38

Luckily

1.37

𝙺

1.37

 while

1.34

Activations Density 0.040%

No Known Activations