© 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. 231753
    Prev
    Next
    INDEX
    Explanations

    forehand winner, Next article, asymmetrical neck

    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
     مجوز
    0.54
     کسب
    0.48
    tarif
    0.47
    Gosudarstvennyj
    0.47
     mô
    0.46
    تج
    0.45
    মো
    0.45
    積
    0.44
    Wiring
    0.44
    toto
    0.44
    POSITIVE LOGITS
     QUE
    0.47
     graças
    0.46
     leaned
    0.45
     dreamed
    0.44
    otle
    0.44
     falou
    0.44
     parlare
    0.44
     kinda
    0.43
     kind
    0.43
    ார்க
    0.43
    Activations Density 0.001%

    No Known Activations