© 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 · 116609 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
116609

INDEX

Explanations

author's transl

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

cmd

-0.75

umani

-0.74

 ASSEMBLY

-0.71

 cúp

-0.70

 intellectual

-0.70

ঋ

-0.70

éron

-0.67

Toxicity

-0.67

 Bolo

-0.66

 TABLES

-0.66

POSITIVE LOGITS

ceous

0.77

origine

0.74

 Kenji

0.69

取

0.66

كار

0.66

board

0.65

ortage

0.65

boxes

0.64

魔女

0.64

zens

0.64

Activations Density 0.081%

No Known Activations