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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37902
    Prev
    Next
    INDEX
    Explanations

    programming syntax and code

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

    This neuron strongly activates on tokens that are parts of URLs, file paths, or programming imports/includes (e.g. domain names, path segments, header or package names).

    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
    改革
    -0.69
     AMPL
    -0.68
     Jaco
    -0.66
    écu
    -0.66
    NOTE
    -0.64
     Barbe
    -0.63
     Judo
    -0.63
    appe
    -0.63
     செ
    -0.63
     pueda
    -0.62
    POSITIVE LOGITS
    mensa
    0.77
     ticker
    0.65
     color
    0.64
    readString
    0.64
    CONTAINER
    0.63
    ∃
    0.63
     bruk
    0.62
     Memphis
    0.62
    OnChange
    0.62
    LECTION
    0.61
    Activations Density 0.072%

    No Known Activations