© 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. 47494
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with parentheses

    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
    葙
    -2.50
    
    -2.38
     is
    -2.36
    縢
    -2.33
    kabau
    -2.30
    堙
    -2.30
    ⎘
    -2.28
    ichtete
    -2.27
    塒
    -2.23
    VIATIONS
    -2.19
    POSITIVE LOGITS
    as
    3.83
    te
    2.72
    翾
    2.45
    us
    2.39
    al
    2.36
    of
    2.22
    >
    2.20
    in
    2.20
    ></
    2.19
    縯
    2.16
    Activations Density 0.004%

    No Known Activations