© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15569
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     when
    -1.61
     also
    -1.54
    伟大
    -1.35
     usually
    -1.33
     often
    -1.33
     always
    -1.28
     mainly
    -1.27
    Suara
    -1.23
     seldom
    -1.23
    </h1>
    -1.22
    POSITIVE LOGITS
     you
    1.70
    我怎么
    1.54
    我现在
    1.49
    厛
    1.43
     dadurch
    1.36
    𐄁
    1.36
     deswegen
    1.34
     który
    1.34
    ricorn
    1.33
     keinerlei
    1.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.