© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 167738
    Prev
    Next
    INDEX
    Explanations

    function declarations

    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
    Negative Logits
    jord
    0.45
     एवरी
    0.44
     אחד
    0.43
    チェーン
    0.42
     chain
    0.41
    clockwise
    0.41
    ৃদ
    0.41
    AVES
    0.40
    ()");
    0.40
    izuje
    0.40
    POSITIVE LOGITS
     природе
    0.42
     особенности
    0.41
    学会
    0.38
     escuelas
    0.38
    缛
    0.38
     природы
    0.38
     PROVIDED
    0.38
     કરવાની
    0.38
     समझे
    0.38
     எடுத்துக்கா
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.