© 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. 126404
    Prev
    Next
    INDEX
    Explanations

    makes working with PDFs simple

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

    ( 语言和标点符号

    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
     accountants
    0.54
     adherents
    0.53
     tribunals
    0.50
     exámenes
    0.48
     orifices
    0.47
     rufis
    0.47
    ʀ
    0.47
    ளோ
    0.46
     نتكلم
    0.46
     চরণ
    0.46
    POSITIVE LOGITS
     valable
    0.47
    (
    0.45
    อบคุณ
    0.43
    טע
    0.43
     winner
    0.43
    ，
    0.43
    ,
    0.41
    <blockquote>
    0.41
     propulsion
    0.40
     Winner
    0.39
    Activations Density 0.000%

    No Known Activations