© 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. 26469
    Prev
    Next
    INDEX
    Explanations

    function definitions and return statements

    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
    stoke
    0.45
     जख
    0.41
    loch
    0.41
     Хо
    0.41
    Sandy
    0.39
     मूत्र
    0.39
    글
    0.38
    壕
    0.38
    ساس
    0.38
     Bie
    0.38
    POSITIVE LOGITS
     returns
    0.43
     precedence
    0.42
     substitute
    0.42
     cast
    0.40
     make
    0.40
     predicate
    0.40
     refine
    0.39
     get
    0.39
     qui
    0.38
     refining
    0.38
    Activations Density 0.007%

    No Known Activations