© 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. 31-GEMMASCOPE-2-RES-262K
    7. 46935
    Prev
    Next
    INDEX
    Explanations

    build optimization

    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_31_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
     aside
    0.49
    t
    0.47
     are
    0.47
     ご
    0.46
    (
    0.46
    ہ
    0.45
     vos
    0.45
     rhet
    0.45
    ف
    0.45
    ()
    0.45
    POSITIVE LOGITS
     гульнявыя
    0.57
    өл
    0.46
     విధంగా
    0.41
    흑
    0.39
    酛
    0.39
    ْن
    0.38
    เพื่อให้
    0.38
    စျေး
    0.38
     professionnelle
    0.38
    Horse
    0.38
    Activations Density 0.003%

    No Known Activations