© 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-3-4B-IT · 22-GEMMASCOPE-2-RES-16K · 7473 ｜ Neuronpedia

Home
Gemma-3-4B-IT
22-GEMMASCOPE-2-RES-16K
7473

INDEX

Explanations

profanity and vulgarity

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-4b-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

Bi

0.97

Slice

0.92

जान

0.90

Advantages

0.86

Body

0.85

Дру

0.83

Height

0.83

Length

0.83

 सज्

0.82

Lone

0.81

POSITIVE LOGITS

 heap

1.27

 strewn

1.27

ocurrency

1.19

heap

1.18

doFilter

1.16

 basura

1.14

fuck

1.13

 garbage

1.08

 jokes

1.06

ulence

1.06

Activations Density 0.216%

No Known Activations