© 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. 91704
    Prev
    Next
    INDEX
    Explanations

    private and assess both

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

    validity beyond

    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
     Zwe
    0.50
     USS
    0.43
    atts
    0.43
     S
    0.42
    uffy
    0.42
    umus
    0.42
     Murphy
    0.40
    requires
    0.40
     U
    0.40
    results
    0.40
    POSITIVE LOGITS
    シェル
    0.49
     wisata
    0.49
    ジャケット
    0.47
    操控
    0.47
     coqu
    0.47
    出口
    0.47
    出演
    0.46
    綺麗
    0.46
    漂亮
    0.45
     viscos
    0.45
    Activations Density 0.001%

    No Known Activations