© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8096
    Prev
    Next
    INDEX
    Explanations

    showing specifics

    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
    //!
    -1.31
    тий
    -1.28
    ある
    -1.27
    asants
    -1.26
     observables
    -1.25
     號
    -1.20
    である
    -1.20
    FUL
    -1.19
     RoutedEventArgs
    -1.19
     لديك
    -1.18
    POSITIVE LOGITS
     how
    1.81
     mostra
    1.68
     muestran
    1.59
     pressão
    1.47
     others
    1.47
     why
    1.41
     diputado
    1.41
     zeigen
    1.38
     montrer
    1.37
    новь
    1.36
    Activations Density 0.139%

    No Known Activations