© 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-3-27B-IT
31-GEMMASCOPE-2-RES-262K
1689
Prev
Next
MODEL
31-gemmascope-2-res-262k
Source/SAE
INDEX
Go
Explanations
numbers following words like 'list of' or 'over'
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
This neuron detects numeric tokens — numbers and numerical quantities (statistics, measurements, years, etc.) in the text.
oai_token-act-pair · gpt-5-mini
Triggered by @yooniel31
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-2-27b-it/resid_post/layer_31_width_262k_l0_medium
How To Load
Prompts (Dashboard)
238,145 prompts, 512 tokens each
Dataset (Dashboard)
lmsys + oasst1
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-3-27b-it/31-gemmascope-2-res-262k/1689?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-3-27b-it/31-gemmascope-2-res-262k/1689?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
愎
0.29
躹
0.26
zdjęcie
0.25
ttino
0.25
þat
0.25
dítě
0.24
څر
0.24
애
0.24
단순히
0.24
instantiation
0.24
POSITIVE LOGITS
5
0.51
3
0.49
7
0.49
4
0.49
8
0.47
6
0.47
six
0.43
9
0.42
2
0.41
1
0.40
Act
ivations
Density 0.268%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
