© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29893
    Prev
    Next
    INDEX
    Explanations

    C++ library headers and code organization

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

    This neuron fires on programming‐language code tokens (especially C++ syntax like angle brackets, #include, template, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ///<
    -0.83
    やっと
    -0.79
     Togo
    -0.78
     potenza
    -0.75
    ッキング
    -0.71
    🌓
    -0.71
    anny
    -0.70
    ⣀
    -0.70
    swal
    -0.70
    peugeot
    -0.70
    POSITIVE LOGITS
     test
    0.90
     prove
    0.79
    ocidade
    0.77
    ints
    0.76
    typedef
    0.76
    逢
    0.75
    IntegrationTest
    0.73
    PathParam
    0.73
    ஃ
    0.73
    不信
    0.72
    Activations Density 0.144%

    No Known Activations