© 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. 31639
    Prev
    Next
    INDEX
    Explanations

    wind

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    chrän
    -0.82
    uggest
    -0.78
    veh
    -0.73
    oco
    -0.72
     לְ
    -0.71
    Aquatic
    -0.71
    legen
    -0.69
    dienne
    -0.69
    PARSE
    -0.68
    worm
    -0.68
    POSITIVE LOGITS
     wind
    6.09
     winds
    4.72
    wind
    4.69
    Wind
    4.53
     Wind
    4.41
     WIND
    3.95
    風
    3.83
    WIND
    3.78
    风
    3.77
     windy
    3.75
    Activations Density 0.112%

    No Known Activations