© 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. 25366
    Prev
    Next
    INDEX
    Explanations

    foreign characters and punctuation

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

    code blocks and code examples

    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
     문제입니다
    0.40
    ถาม
    0.38
    วด
    0.37
     경우가
    0.37
     Frage
    0.37
     اوقات
    0.36
    악
    0.36
    lossen
    0.35
    이스
    0.35
     사람들이
    0.35
    POSITIVE LOGITS
    <code>
    0.45
     cartão
    0.43
     sekä
    0.41
    дә
    0.41
    ,“
    0.40
    密码
    0.40
    ómetro
    0.40
    ഗി
    0.40
     botón
    0.40
     dönt
    0.40
    Activations Density 0.002%

    No Known Activations