© 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. 23021
    Prev
    Next
    INDEX
    Explanations

    export India

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

    technical topics with explanations

    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
     布
    0.45
     مخالف
    0.44
     تولید
    0.43
     जल्द
    0.40
    尽快
    0.40
    DELETE
    0.40
    欣
    0.39
    肴
    0.39
    促進
    0.39
     veículo
    0.39
    POSITIVE LOGITS
     étro
    0.48
     convexes
    0.47
     Which
    0.47
     are
    0.46
     interes
    0.46
     связаны
    0.45
     najbli
    0.43
     WHICH
    0.43
     which
    0.43
    ຂໍ້ມ
    0.43
    Activations Density 0.000%

    No Known Activations