© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3134
    Prev
    Next
    INDEX
    Explanations

    code constructs and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zeitschr
    0.29
     voci
    0.28
     veramente
    0.27
     adoles
    0.26
     Schauspiel
    0.26
     ঘুম
    0.26
     Madame
    0.26
    滟
    0.26
     Pattes
    0.26
     Francesca
    0.25
    POSITIVE LOGITS
    if
    0.44
    //
    0.35
    return
    0.31
    formatted
    0.30
    var
    0.30
    let
    0.30
    reate
    0.30
    #
    0.30
    <!--
    0.29
    for
    0.29
    Activations Density 0.195%

    No Known Activations