© 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. 12406
    Prev
    Next
    INDEX
    Explanations

    may cover

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

    list items with examples

    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
    IS
    0.47
    lex
    0.45
    -
    0.44
    वे
    0.44
    olly
    0.43
    stru
    0.42
    ann
    0.42
    let
    0.41
    It
    0.41
     "
    0.41
    POSITIVE LOGITS
     lèvres
    0.70
     zespół
    0.59
     belakang
    0.57
    amı
    0.56
    یف
    0.55
     bırak
    0.55
     manglid
    0.55
     jornalista
    0.55
     veines
    0.55
     sólida
    0.55
    Activations Density 0.000%

    No Known Activations