© 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. 146289
    Prev
    Next
    INDEX
    Explanations

    cross-lingual semantic association

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

    individuals benefit

    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
    B
    0.56
    타고
    0.55
    m
    0.54
    sning
    0.52
    탔
    0.47
    ופי
    0.47
    ))){
    0.46
    ధు
    0.46
    야
    0.46
    د
    0.45
    POSITIVE LOGITS
     ਸਮ
    0.52
     よく
    0.51
     よろしく
    0.50
     によって
    0.49
     グラ
    0.49
     藤
    0.48
     など
    0.48
     ベビー
    0.47
     semelh
    0.47
     ตอบ
    0.46
    Activations Density 0.001%

    No Known Activations