© 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
Home
Gemma-2-27B
22-GEMMASCOPE-RES-131K
34223
Prev
Next
MODEL
22-gemmascope-res-131k
Source/SAE
INDEX
Go
Explanations
length contributes
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
The neuron is strongly activated by numeric tokens and identifiers—e.g. integers, decimals, and long alphanumeric IDs—highlighting passages that contain numbers or number‐like strings.
oai_token-act-pair · o4-mini
Triggered by @jyhe0408
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_22/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/22-gemmascope-res-131k/34223?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/22-gemmascope-res-131k/34223?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
”:
-1.23
ｪ
-1.07
ТОВ
-1.07
siè
-1.07
䊊
-1.07
ƭ
-1.07
enfans
-1.05
öffentlichen
-1.05
Diſ
-1.05
compró
-1.05
POSITIVE LOGITS
â
1.10
«
1.06
is
1.02
1.00
0.98
不时
0.96
\"
0.94
0.94
ണ
0.90
Does
0.90
Act
ivations
Density 0.205%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
