© 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. 79133
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    numbers and quantities

    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
     څه
    0.59
     எம்
    0.56
     to
    0.55
     অংশে
    0.55
     ارو
    0.55
     құ
    0.54
     اسمها
    0.54
    })]
    0.54
     দে
    0.54
     もの
    0.54
    POSITIVE LOGITS
    0.66
     hundred
    0.61
     fours
    0.57
     Hundred
    0.56
     thousand
    0.54
     Cherokee
    0.54
     Seven
    0.53
     threes
    0.50
     cricketer
    0.50
     birthday
    0.49
    Activations Density 0.198%

    No Known Activations