© 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-16K
    7. 11725
    Prev
    Next
    INDEX
    Explanations

    function call or declaration

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

    function calls and definitions

    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_16k_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
    i
    0.67
     novels
    0.46
    3
    0.46
     cierto
    0.45
     yıldır
    0.45
     তর্ক
    0.45
     censoring
    0.45
    ans
    0.44
    antd
    0.44
     censor
    0.44
    POSITIVE LOGITS
     (){
    0.64
     Х
    0.59
     Б
    0.55
     "("
    0.55
     Уни
    0.54
    ックス
    0.53
    ?(
    0.53
    к
    0.52
     '('
    0.50
    `(
    0.50
    Activations Density 0.001%

    No Known Activations