© 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. 34-GEMMASCOPE-RES-131K
    4. 47769
    Prev
    Next
    INDEX
    Explanations

    c++ type declarations

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

    The neuron strongly activates on C/C++ preprocessor include directives (the “#include <…>” or “#include "…"” lines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     évolu
    -0.93
    TInt
    -0.92
     jeżeli
    -0.88
    helped
    -0.86
     Int
    -0.76
    rigated
    -0.76
    cepan
    -0.75
     Russo
    -0.75
    tovat
    -0.73
    轎
    -0.73
    POSITIVE LOGITS
    uint
    1.30
     uint
    1.17
     excru
    0.83
    дах
    0.78
    size
    0.77
    void
    0.75
     Feeds
    0.75
     Aggression
    0.75
    /${
    0.75
    diging
    0.74
    Activations Density 0.036%

    No Known Activations