© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2766
    Prev
    Next
    INDEX
    Explanations

    LaTeX sectioning commands

    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_262k_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
    يذ
    0.46
    ूरिया
    0.42
    姦
    0.42
    嵋
    0.42
    razine
    0.41
     Yards
    0.41
    ⣶
    0.41
    yards
    0.39
     Wyatt
    0.38
    भि
    0.38
    POSITIVE LOGITS
    *{
    0.52
    *{\
    0.47
     {\
    0.38
     mark
    0.38
    {}\
    0.37
    {\
    0.36
    mark
    0.35
    Hepinize
    0.35
    {"
    0.34
    Properties
    0.34
    Activations Density 0.000%

    No Known Activations