© 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-2-27B · 34-GEMMASCOPE-RES-131K · 76942 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
76942

INDEX

Explanations

episode titles

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_34/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

 based

-0.98

喊道

-0.94

 antwortete

-0.87

 Werkstatt

-0.84

seamnă

-0.83

ụn

-0.80

 contributed

-0.78

క్క

-0.77

motorola

-0.77

طنين

-0.76

POSITIVE LOGITS

ênero

0.97

gamento

0.96

 Faure

0.89

ritch

0.89

蛊

0.87

β

0.85

protective

0.83

ITIS

0.83

нин

0.83

 LIBR

0.82

Activations Density 0.019%

No Known Activations