© 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. 227952
    Prev
    Next
    INDEX
    Explanations

    computing or access

    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
     célé
    0.43
    tracer
    0.43
     Italien
    0.42
    chacha
    0.41
    ੫
    0.41
     dern
    0.41
    dj
    0.41
    asse
    0.41
    hiya
    0.41
    atrice
    0.39
    POSITIVE LOGITS
    WORTH
    0.56
    ToBounds
    0.53
     將
    0.50
     enjoined
    0.48
    İZ
    0.47
     nấu
    0.47
    囤
    0.47
     Amount
    0.46
    None
    0.46
    パーカー
    0.46
    Activations Density 0.000%

    No Known Activations