© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2204
    Prev
    Next
    INDEX
    Explanations

    clothing, objects, and places

    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_40_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
     eg
    0.36
     ub
    0.36
     구성
    0.36
     oluştur
    0.33
     පේශ
    0.33
     våra
    0.32
    <0x0E>
    0.32
     Ew
    0.32
     cenderung
    0.32
    颦
    0.32
    POSITIVE LOGITS
    лган
    0.34
    ボー
    0.33
     cheerful
    0.30
    யில்
    0.29
     hotel
    0.29
    мент
    0.29
    long
    0.29
    ባት
    0.29
     convent
    0.29
    েলের
    0.29
    Activations Density 0.003%

    No Known Activations