© 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. 4367
    Prev
    Next
    INDEX
    Explanations

    weight loss and health supplements

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

    medical substances and conditions

    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
     квадрат
    0.35
    പാട
    0.35
    棂
    0.35
    ຂໍ້ມູນ
    0.34
     ডকুম
    0.34
     beragam
    0.34
     sequência
    0.33
    Calibration
    0.33
     gần
    0.33
     aufgrund
    0.33
    POSITIVE LOGITS
     gummies
    0.32
    <start_of_image>
    0.32
    if
    0.32
    ivan
    0.31
     sighed
    0.31
    iblock
    0.29
    %}
    0.29
    hy
    0.28
    ({
    0.28
    warts
    0.28
    Activations Density 0.000%

    No Known Activations