© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-3-1B-IT · 22-GEMMASCOPE-2-RES-16K · 4000 ｜ Neuronpedia

Home
Gemma-3-1B-IT
22-GEMMASCOPE-2-RES-16K
4000

INDEX

Explanations

data analysis and security

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

輌

0.83

 subsets

0.83

 pairs

0.74

 rentals

0.74

ού

0.72

roups

0.72

‌های

0.72

ेप

0.71

ፈ

0.69

 samples

0.69

POSITIVE LOGITS

 security

0.78

 seguridad

0.76

 keamanan

0.75

セキュリティ

0.74

security

0.69

Security

0.68

Die

0.68

Das

0.68

Secure

0.67

CPU

0.67

Activations Density 0.095%

No Known Activations