© 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. 150727
    Prev
    Next
    INDEX
    Explanations

    run every, risk of

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

    a defined

    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
     透
    0.52
     ন
    0.48
     可能
    0.48
     可
    0.47
     เข้า
    0.45
     黑
    0.45
    文档
    0.45
     哈
    0.45
     ตั้ง
    0.45
     Hän
    0.44
    POSITIVE LOGITS
    вання
    0.64
    k
    0.45
    дится
    0.45
    ни
    0.44
     bombardment
    0.44
    self
    0.43
    lanelet
    0.43
    deploy
    0.42
    setAuto
    0.42
    createdBy
    0.41
    Activations Density 0.000%

    No Known Activations