© 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. 170590
    Prev
    Next
    INDEX
    Explanations

    increasing the, call us

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

    circle icon emblem del Sol

    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
    
    0.50
     пары
    0.49
     மிகப்பெ
    0.46
    <unused382>
    0.46
     HttpServer
    0.46
     ხელისუფლების
    0.45
    প্রিম
    0.44
    嘩
    0.44
    ראה
    0.43
     অবশ্যই
    0.43
    POSITIVE LOGITS
    j
    0.59
    in
    0.57
    t
    0.56
    li
    0.54
    z
    0.52
    l
    0.51
    a
    0.51
    r
    0.50
    zc
    0.49
    沐
    0.48
    Activations Density 0.001%

    No Known Activations