© 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 · 127771 ｜ Neuronpedia
Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
127771
Prev
Next
MODEL
10-gemmascope-res-131k
Source/SAE
INDEX
Go
Explanations
place names followed by county or township
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
The neuron activates on substrings that are parts of geographic place names (e.g. common town/village or street name elements).
oai_token-act-pair · o4-mini
Triggered by @jyhe0408
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
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/127771?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/127771?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
檮
-2.19
レスト
-2.17
夜景
-2.16
鱨
-2.11
嘖
-2.06
锱
-2.05
餍
-1.99
⽼
-1.99
︕
-1.98
拶
-1.97
POSITIVE LOGITS
↵↵
2.17
*
2.11
I
2.06
}\
1.95
})$
1.88
’
1.82
1.81
For
1.80
slight
1.73
.“
1.73
Act
ivations
Density 0.140%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
