© 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. 22617
    Prev
    Next
    INDEX
    Explanations

    titles and names

    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
    Negative Logits
    ;
    -1.57
    '
    -1.51
     potrebbe
    -1.46
    _
    -1.45
     pourrait
    -1.42
     its
    -1.40
    -1.37
     Its
    -1.33
     pensez
    -1.32
     the
    -1.30
    POSITIVE LOGITS
     propOrder
    1.58
    ії
    1.51
    </strong>
    1.45
    neaux
    1.43
    ickness
    1.38
     Wartawan
    1.38
    enment
    1.37
    ingale
    1.37
    erapeutics
    1.37
     Некоторые
    1.36
    Activations Density 0.103%
    No Known Activations