© 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 · 34-GEMMASCOPE-RES-131K · 4341 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
4341

INDEX

Explanations

ne, N(e), new

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

targets

-0.83

 Targets

-0.81

WIB

-0.80

 scheduler

-0.79

 targets

-0.77

GAL

-0.77

 détente

-0.77

LEG

-0.76

 vene

-0.75

 Arend

-0.75

POSITIVE LOGITS

Ne

1.04

Ne

1.02

ne

0.79

单

0.76

gtr

0.73

mid

0.73

out

0.71

 Не

0.71

 entirely

0.70

allure

0.70

Activations Density 0.072%

No Known Activations