© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22480
    Prev
    Next
    INDEX
    Explanations

    This program is free software

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

    The neuron activates on decorative comment‐header lines (especially those starting with “*” or similar markers) in license headers.

    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
    ⛥
    -1.70
     современных
    -1.69
     наших
    -1.64
     naszej
    -1.63
     нашем
    -1.63
    musica
    -1.57
     takich
    -1.55
     polska
    -1.55
     naszego
    -1.55
    ⠀⠀⠀⠀⠀⠀⠀⠀
    -1.55
    POSITIVE LOGITS
     also
    1.91
     at
    1.82
     of
    1.77
     to
    1.77
     for
    1.74
     or
    1.68
     a
    1.66
     not
    1.60
     in
    1.59
     during
    1.55
    Activations Density 0.050%

    No Known Activations