© 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. 234113
    Prev
    Next
    INDEX
    Explanations

    photo function

    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
    卡塔尔
    0.52
     выз
    0.50
     conceptual
    0.50
    ка
    0.50
     rut
    0.49
    /
    0.48
     конфигура
    0.48
    НО
    0.46
     deserial
    0.46
    anomaly
    0.46
    POSITIVE LOGITS
    ﻢ
    0.46
    odnev
    0.43
     Indust
    0.42
    essere
    0.42
     lemak
    0.42
    振動
    0.42
     مصنوع
    0.41
    drying
    0.40
    INTERFACE
    0.40
     े
    0.40
    Activations Density 0.001%

    No Known Activations