© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 43889
    Prev
    Next
    INDEX
    Explanations

    numbering sections or pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     can
    0.73
     čís
    0.72
     чисел
    0.71
    د
    0.71
     число
    0.68
     рішення
    0.68
    д
    0.67
     العدد
    0.67
     деталей
    0.66
     संख्या
    0.65
    POSITIVE LOGITS
    し
    0.75
    不要
    0.73
    ブラ
    0.71
    /
    0.66
     (
    0.66
    entious
    0.64
    さ
    0.63
    通
    0.63
    harap
    0.63
    ラ
    0.63
    Activations Density 0.002%

    No Known Activations