© 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. 16624
    Prev
    Next
    INDEX
    Explanations

    RSS 2.0 feed

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

    QD NU sequence

    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
    Prz
    0.39
    bk
    0.38
     Einstellungen
    0.38
     ਦਾ
    0.38
     ›
    0.38
     altid
    0.37
     কর্প
    0.37
     लगाए
    0.37
     शुल्क
    0.37
    <0xE1>
    0.37
    POSITIVE LOGITS
    なかった
    0.38
    assapi
    0.37
    GENERAL
    0.36
    JSPA
    0.35
    흠
    0.35
    ையா
    0.33
    Ongoing
    0.33
     lingering
    0.33
     referência
    0.33
    жны
    0.32
    Activations Density 0.017%

    No Known Activations