© 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. 162986
    Prev
    Next
    INDEX
    Explanations

    stage of property

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

    making it simpler, faster, or reliable

    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
    rt
    0.50
    h
    0.49
    scroll
    0.46
    n
    0.43
    ning
    0.43
    d
    0.43
     वर्णित
    0.43
    xlsx
    0.42
    rg
    0.42
    t
    0.42
    POSITIVE LOGITS
    Ꮡ
    0.54
     leukocyte
    0.50
    HEIM
    0.49
     Leibnitz
    0.49
    ٻ
    0.49
    メイド
    0.48
    を知
    0.48
    맛집
    0.47
    얘
    0.46
     obstetric
    0.46
    Activations Density 0.000%

    No Known Activations