© 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. 73368
    Prev
    Next
    INDEX
    Explanations

    static code declarations

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

    The neuron strongly activates on the “static” keyword (i.e. C/C++ static declarations).

    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
     to
    -2.28
     ihtiyaç
    -1.89
     "
    -1.89
     detayl
    -1.80
     yaklaş
    -1.59
     The
    -1.58
     detaylı
    -1.57
     misschien
    -1.55
     ("
    -1.48
    螣
    -1.47
    POSITIVE LOGITS
    ”,
    1.89
     спросил
    1.79
    ”:
    1.74
    y
    1.72
    」，
    1.72
    ”،
    1.68
    Ꮸ
    1.67
     shouldn
    1.66
    am
    1.64
    ］
    1.63
    Activations Density 0.009%

    No Known Activations