© 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. 226340
    Prev
    Next
    INDEX
    Explanations

    WE CREATE

    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
     其
    0.58
    XPath
    0.47
     Outs
    0.47
     duckys
    0.47
     Còn
    0.46
    頁
    0.45
    DVRIP
    0.44
     SharePoint
    0.44
     spongy
    0.43
     Gutiérrez
    0.43
    POSITIVE LOGITS
    oglobulin
    0.47
    운
    0.47
    i
    0.47
     on
    0.46
    போது
    0.46
    ré
    0.43
     powiet
    0.43
    काब
    0.43
    สิ่ง
    0.43
     cao
    0.43
    Activations Density 0.001%

    No Known Activations