© 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. 24312
    Prev
    Next
    INDEX
    Explanations

    induction cooktop

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

    referenced songs/movies

    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
    НЕ
    0.44
    нет
    0.39
     NORTH
    0.38
    ე
    0.36
    ो
    0.35
    аб
    0.35
     Бар
    0.35
     임
    0.34
     '.</
    0.34
    亅
    0.34
    POSITIVE LOGITS
    时间和
    0.35
    tudo
    0.35
     খাবার
    0.32
     نكمل
    0.30
    நபியே
    0.30
    ကြာ
    0.30
    皁
    0.30
     zarówno
    0.30
    俶
    0.30
     både
    0.30
    Activations Density 0.198%

    No Known Activations