© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59072
    Prev
    Next
    INDEX
    Explanations

    Restaurant Group

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on comma separators ("," tokens) in code or data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    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
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     και
    -2.55
     și
    -2.50
    และ
    -2.33
    \
    -2.25
     và
    -2.25
     и
    -2.08
    رحلة
    -2.02
     یا
    -1.98
     และ
    -1.94
     of
    -1.88
    POSITIVE LOGITS
     the
    3.64
     a
    2.39
    re
    2.09
     gescha
    2.03
    急忙
    1.92
    is
    1.87
    銪
    1.85
     involucra
    1.82
     geringe
    1.80
     garantiza
    1.79
    Activations Density 0.012%

    No Known Activations