© 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. 157587
    Prev
    Next
    INDEX
    Explanations

    writing specific things

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

    Huawei networks, capacities, Windows drivers

    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
     wybra
    0.50
    amię
    0.49
     พัน
    0.49
     aprend
    0.47
    蛳
    0.46
     THAN
    0.46
     Loài
    0.46
    ഹ്ലാ
    0.46
     เดือน
    0.46
     settimane
    0.45
    POSITIVE LOGITS
     مثبت
    0.42
    不多
    0.41
    oweit
    0.41
    3
    0.41
     кеңсе
    0.40
    يس
    0.40
    Def
    0.39
     résult
    0.39
    ობით
    0.39
     radiators
    0.39
    Activations Density 0.001%

    No Known Activations