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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42107
    Prev
    Next
    INDEX
    Explanations

    function calls and definitions

    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
     RoutedEventArgs
    -1.40
     envelo
    -1.38
     assurer
    -1.38
     этих
    -1.34
     Quando
    -1.32
     garantir
    -1.31
     certains
    -1.30
     términos
    -1.30
     milliard
    -1.30
    compared
    -1.29
    POSITIVE LOGITS
     about
    2.56
     in
    2.44
     for
    2.33
     based
    2.03
     as
    1.96
     by
    1.96
     on
    1.91
     with
    1.89
     without
    1.77
     regarding
    1.77
    Activations Density 0.086%

    No Known Activations