© 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. 62577
    Prev
    Next
    INDEX
    Explanations

    monitor services and data

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

    code examples and explanations

    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
    $，
    0.54
    discount
    0.50
     tertinggi
    0.46
    keycode
    0.46
    ಎಸ್
    0.43
    IsIn
    0.43
     discount
    0.43
    ”;
    0.43
     dance
    0.43
     genre
    0.42
    POSITIVE LOGITS
    จำ
    0.48
     कामका
    0.46
     ไม่
    0.45
     Handler
    0.45
     Faulkner
    0.44
     Putt
    0.44
     плана
    0.44
    漪
    0.44
    дели
    0.43
    วัสดี
    0.43
    Activations Density 0.000%

    No Known Activations