© 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. 34-GEMMASCOPE-RES-131K
    7. 78345
    Prev
    Next
    INDEX
    Explanations

    Win APIs

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

    The neuron activates on mentions of the Windows “Win32” (and related Windows API) terms.

    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
    嬢
    -0.77
    adova
    -0.75
    Falls
    -0.73
     ostensibly
    -0.73
     overflows
    -0.71
     ironically
    -0.71
     impressively
    -0.70
     Referral
    -0.69
    alumno
    -0.69
    <bos>
    -0.68
    POSITIVE LOGITS
    sock
    0.87
     Spalding
    0.86
    bond
    0.85
    api
    0.83
    ㉒
    0.82
    API
    0.81
    teros
    0.81
    ulateur
    0.80
     Casanova
    0.80
     API
    0.80
    Activations Density 0.020%

    No Known Activations