© 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. 110566
    Prev
    Next
    INDEX
    Explanations

    code and mixed languages

    np_acts-logits-general · gemini-2.5-flash-lite

    opening braces of function or method definitions in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    囖
    -1.49
     zrobić
    -1.45
     przycis
    -1.41
    ěř
    -1.31
    鼉
    -1.30
    狁
    -1.29
     dne
    -1.28
    propertyName
    -1.27
    tokenId
    -1.24
     wektor
    -1.24
    POSITIVE LOGITS
     of
    1.68
     ediyor
    1.48
     that
    1.41
     químicas
    1.41
     odası
    1.34
     zove
    1.30
    ?
    1.30
     with
    1.26
    他に
    1.22
     pandémie
    1.17
    Activations Density 0.014%

    No Known Activations