© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 243497
    Prev
    Next
    INDEX
    Explanations

    sporting activities and games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jama
    0.45
    ya
    0.44
    arovski
    0.43
    baseline
    0.43
    $-$
    0.43
    inée
    0.43
    शुदा
    0.43
    kam
    0.42
    sgál
    0.42
    妸
    0.42
    POSITIVE LOGITS
     recreational
    0.54
     domeni
    0.52
     théorie
    0.47
     Brou
    0.47
     geotechnical
    0.46
    يف
    0.45
     tahun
    0.44
     cunoscut
    0.44
     saloon
    0.44
     Chihuahua
    0.44
    Activations Density 0.000%

    No Known Activations