© 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-262K
    7. 247442
    Prev
    Next
    INDEX
    Explanations

    party members

    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
    Not in Any Lists

    No Comments

    Negative Logits
    wezig
    0.48
    APP
    0.47
    tableName
    0.47
    රක
    0.46
    nst
    0.46
    dets
    0.46
    𝚖
    0.46
    ren
    0.45
    unsigned
    0.45
    OBJ
    0.45
    POSITIVE LOGITS
     sarebbero
    0.52
    創作
    0.49
     thành
    0.48
     Recurs
    0.46
    ทาง
    0.46
     असतील
    0.46
    成
    0.44
    会导致
    0.43
     bày
    0.41
     nell
    0.41
    Activations Density 0.001%

    No Known Activations