© 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. 22-GEMMASCOPE-RES-131K
    7. 65288
    Prev
    Next
    INDEX
    Explanations

    database queries and api calls

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

    This neuron activates on code tokens involved in database query calls or method‐chaining for fetching data (e.g. “->query”, “->get”, “->where”, “db”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     muualla
    -0.95
     riesce
    -0.94
    logg
    -0.94
    hua
    -0.94
    weighed
    -0.93
     produs
    -0.93
    glMatrix
    -0.93
    natured
    -0.90
     {
    -0.88
    hhh
    -0.88
    POSITIVE LOGITS
     nahezu
    1.12
     it
    1.02
     малень
    0.96
    siehe
    0.96
    資料來源
    0.95
    谥
    0.95
    なります
    0.95
     small
    0.95
     aceptas
    0.92
    edance
    0.91
    Activations Density 0.002%

    No Known Activations