© 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. 4215
    Prev
    Next
    INDEX
    Explanations

    stage or period

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

    steps, columns, layers, turns

    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
    yı
    0.55
    eşit
    0.55
    4
    0.54
    ya
    0.48
     parç
    0.48
    year
    0.47
    i
    0.47
     রকম
    0.46
    y
    0.46
    ４
    0.45
    POSITIVE LOGITS
    ของการ
    0.77
     của
    0.70
     of
    0.66
    ของ
    0.61
     của
    0.57
    에서의
    0.55
    中的
    0.53
    的大
    0.53
    នៃ
    0.53
     notificações
    0.48
    Activations Density 0.244%

    No Known Activations