© 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. 82610
    Prev
    Next
    INDEX
    Explanations

    function calls and programming constructs

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

    variable assignments

    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
    URE
    0.44
     essai
    0.44
    ｐ
    0.44
    essai
    0.42
    UMI
    0.42
    Ｔ
    0.41
    CN
    0.41
    かん
    0.40
    ACT
    0.40
    Ｇ
    0.40
    POSITIVE LOGITS
     étant
    0.42
     بدء
    0.42
    getFrom
    0.41
     GetComponent
    0.40
     Heartland
    0.40
     Elo
    0.39
    셔야
    0.39
     Fam
    0.38
     Reformation
    0.38
     tho
    0.38
    Activations Density 0.000%

    No Known Activations