© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 100475 ｜ Neuronpedia
Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
100475
Prev
Next
MODEL
10-gemmascope-res-131k
Source/SAE
INDEX
Go
Explanations
information leaks
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
the word "leaked" and related contexts involving information or data breaches.
oai_token-act-pair · claude-4-5-sonnet
Triggered by @bfgcn7frf5
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-27b-pt-res/layer_10/width_131k
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-27b/10-gemmascope-res-131k/100475?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-27b/10-gemmascope-res-131k/100475?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
-2.11
↵↵
-2.08
-2.05
-2.02
-1.95
-1.95
刧
-1.93
You
-1.85
-1.83
In
-1.81
POSITIVE LOGITS
wakili
2.11
谖
2.03
臜
1.98
rahasia
1.98
accedi
1.94
kekasih
1.91
Lokal
1.90
berusia
1.89
antaranya
1.88
colchón
1.88
Act
ivations
Density 0.008%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
