© 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. 101421
    Prev
    Next
    INDEX
    Explanations

    explanation or definition

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

    modify, rule, performance, reports, limited

    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
    maktadır
    0.51
     ու
    0.51
    cı
    0.48
    嘚
    0.48
    业协会
    0.47
    aya
    0.47
    ứa
    0.46
     పు
    0.46
    llan
    0.45
     аспек
    0.45
    POSITIVE LOGITS
    ק
    0.54
    വോ
    0.52
    غ
    0.51
    GOD
    0.50
    ือบ
    0.50
    ز
    0.48
    ک
    0.48
    ラー
    0.48
    Rb
    0.47
    EDUCATION
    0.47
    Activations Density 0.001%

    No Known Activations