© 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. 21691
    Prev
    Next
    INDEX
    Explanations

    function signatures and types

    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
     "
    -1.64
    埝
    -1.48
     EVEN
    -1.44
     vermel
    -1.38
    眚
    -1.35
    粜
    -1.35
    /">
    -1.30
     ห
    -1.29
     primeiro
    -1.27
     vielen
    -1.27
    POSITIVE LOGITS
     such
    1.62
     suoi
    1.61
     with
    1.52
     makes
    1.52
     seems
    1.46
     paradiso
    1.44
     Ihm
    1.43
     two
    1.39
     still
    1.38
     allows
    1.35
    Activations Density 0.019%

    No Known Activations