© 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. 241827
    Prev
    Next
    INDEX
    Explanations

    giveaway ends, 2 controllers

    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
    udiante
    0.46
    عي
    0.44
    ıyor
    0.44
    邮箱
    0.43
    тра
    0.43
    يلي
    0.43
    bentuk
    0.43
    d
    0.42
    ırs
    0.42
     verificación
    0.42
    POSITIVE LOGITS
    ぐるみ
    0.50
     いく
    0.47
     mashed
    0.46
     modulates
    0.45
     od
    0.44
     vanno
    0.43
     crockery
    0.43
     重要
    0.43
     त्याच्या
    0.41
     converges
    0.41
    Activations Density 0.001%

    No Known Activations