© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104370
    Prev
    Next
    INDEX
    Explanations

    gaming stays

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

    technical descriptions with AI

    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
    ล
    0.52
    ल
    0.50
    ๊
    0.49
    ้
    0.48
    ئی
    0.48
    データの
    0.48
    เช
    0.46
    Ups
    0.46
    ผล
    0.46
    ใช้
    0.45
    POSITIVE LOGITS
    hattim
    0.55
    zovaniyu
    0.52
     கட்டுமானம்
    0.50
    궐
    0.48
    龕
    0.48
     Конгрегация
    0.47
    нок
    0.47
     variación
    0.47
     imasmim
    0.47
     కాని
    0.46
    Activations Density 0.000%

    No Known Activations