© 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. 76456
    Prev
    Next
    INDEX
    Explanations

    if you want

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

    And

    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
     lorsqu
    0.48
    }}_{\
    0.41
    QQ
    0.41
    jsdel
    0.41
    デー
    0.40
    $&
    0.40
    ティック
    0.39
    Prop
    0.39
    thats
    0.39
    Quando
    0.38
    POSITIVE LOGITS
    এবং
    0.43
     He
    0.40
     History
    0.40
     และ
    0.40
    ุณ
    0.39
    咊
    0.39
     статистики
    0.38
     Grammar
    0.38
    耷
    0.37
     ahí
    0.37
    Activations Density 0.009%

    No Known Activations