© 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. 83987
    Prev
    Next
    INDEX
    Explanations

    UI components and initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -1.67
     pomocou
    -1.46
     inability
    -1.41
     Aufmerksamkeit
    -1.38
     possesses
    -1.37
     wahre
    -1.37
     totiž
    -1.36
    nachron
    -1.36
    りましたが
    -1.32
     latter
    -1.30
    POSITIVE LOGITS
    vensko
    1.38
    UUUU
    1.29
    ホルダー
    1.27
    </h2>
    1.21
    РС
    1.20
     оставить
    1.17
     faciles
    1.16
     tristes
    1.16
     éter
    1.16
     rése
    1.16
    Activations Density 0.110%

    No Known Activations