© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71018
    Prev
    Next
    INDEX
    Explanations

    keywords, Explorer Edition, authorization, notify

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

    activation, increasingly, resource, frequently

    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
    Negative Logits
     प्रथ
    0.52
     knockout
    0.52
     retouch
    0.49
     nonprofits
    0.49
     discounts
    0.48
     oaths
    0.48
     invite
    0.48
     scholarships
    0.48
    夗
    0.47
    വ്ര
    0.47
    POSITIVE LOGITS
    ERR
    0.50
    ZER
    0.50
    ui
    0.47
    جيل
    0.44
    blah
    0.44
    AMP
    0.44
    <0xAF>
    0.43
    ;%(
    0.43
    por
    0.43
     سننے
    0.43
    Activations Density 0.000%

    No Known Activations