© 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. 231449
    Prev
    Next
    INDEX
    Explanations

    people you can’t stand

    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
    ｻ
    0.54
    ﾞ
    0.47
    Ъ
    0.47
    ウッド
    0.46
     insults
    0.46
     auditions
    0.46
    ｬ
    0.45
    ्टर
    0.44
     اولین
    0.44
    のと
    0.44
    POSITIVE LOGITS
     Plante
    0.45
    div
    0.44
    cs
    0.44
    da
    0.44
     Barrie
    0.43
    ya
    0.43
    cmd
    0.43
    .<
    0.43
    ská
    0.43
     korzyst
    0.43
    Activations Density 0.000%

    No Known Activations