© 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. 168733
    Prev
    Next
    INDEX
    Explanations

    blended into variety

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

    length, much, implied, sure, mind, contributing, books

    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
    을
    0.52
    ：
    0.51
     webinars
    0.47
    のこ
    0.47
     முதல்வர்
    0.46
    은
    0.46
    喵
    0.46
     فيديو
    0.45
    "]:
    0.45
    は
    0.44
    POSITIVE LOGITS
     familiale
    0.45
    ALTERNATIVNAMEN
    0.45
     Famil
    0.44
     متفاوت
    0.42
     rem
    0.41
    UniqueIdentifier
    0.41
     Ausdruck
    0.41
    ક્ષા
    0.41
     Aussi
    0.41
    uttosto
    0.41
    Activations Density 0.002%

    No Known Activations