© 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 · 32924 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
32924

INDEX

Explanations

legal documents

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

Ď

-1.05

logitech

-1.04

Ayrıca

-1.04

为什么

-0.99

ᅱ

-0.98

 misschien

-0.96

Če

-0.96

Från

-0.95

$[

-0.92

Lycka

-0.92

POSITIVE LOGITS

 other

0.88

Usa

0.86

udesta

0.85

лкой

0.84

 другая

0.82

 marinas

0.82

blum

0.81

0.81

 percent

0.81

่วง

0.81

Activations Density 0.004%

No Known Activations