Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-3-1B-IT
17-GEMMASCOPE-2-RES-16K
556
Prev
Next
MODEL
17-gemmascope-2-res-16k
Source/SAE
INDEX
Go
Explanations
The neuron detects section headings and document-structure markers (titles, numbered list entries and other section-start tokens) across languages.
oai_token-act-pair · gpt-5-mini
Triggered by @toaster
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
gg-gs/gemma-scope-2-1b-it/resid_post
Prompts (Dashboard)
273,612 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-3-1b-it/17-gemmascope-2-res-16k/556?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-3-1b-it/17-gemmascope-2-res-16k/556?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
0.92
in
0.73
(
0.72
a
0.72
is
0.67
one
0.66
and
0.62
with
0.62
,
0.61
T
0.61
POSITIVE LOGITS
𒋖
1.10
𒅰
1.10
𒆝
1.10
getNFiles
1.09
𒅾
1.09
𒍋
1.09
𒃞
1.09
Ioctrl
1.09
𒍌
1.09
𒃘
1.09
Act
ivations
Density 1.273%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
