© 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. 248974
    Prev
    Next
    INDEX
    Explanations

    conference, functions, techniques, village

    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
    ラブ
    0.47
    રી
    0.46
    コン
    0.46
     toolbox
    0.46
    ocommit
    0.45
     Myths
    0.44
    ｻ
    0.44
     SAV
    0.44
    无可
    0.43
     fireworks
    0.43
    POSITIVE LOGITS
    {,}
    0.52
    otas
    0.49
    sg
    0.49
    dados
    0.48
    ald
    0.48
    ane
    0.47
    ofy
    0.47
    óny
    0.47
    ᱼ
    0.47
    supp
    0.46
    Activations Density 0.001%

    No Known Activations