© 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. 34-GEMMASCOPE-RES-131K
    7. 93985
    Prev
    Next
    INDEX
    Explanations

    public static void declarations

    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_34/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
     our
    -1.03
     because
    -0.95
     there
    -0.93
     jemand
    -0.88
     именно
    -0.88
     astfel
    -0.86
    閲覧
    -0.85
     până
    -0.85
     Gnade
    -0.82
    かもしれません
    -0.81
    POSITIVE LOGITS
     void
    3.83
    void
    3.75
     will
    2.97
     would
    2.09
     voids
    1.82
    จะ
    1.81
     sẽ
    1.57
     to
    1.50
     akan
    1.37
    VOID
    1.33
    Activations Density 0.035%

    No Known Activations