© 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. 110647
    Prev
    Next
    INDEX
    Explanations

    ServiceModel DataContract WCF

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

    Windows Communication Foundation (WCF) service-related code and terminology.

    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
     zewnętrzne
    -1.58
     halbe
    -1.54
     zmiany
    -1.54
    medriver
    -1.49
    ทั้ง
    -1.47
    皷
    -1.47
     mangled
    -1.45
    ｢
    -1.45
     gioca
    -1.45
    itosan
    -1.45
    POSITIVE LOGITS
    Y
    1.75
    ↵↵
    1.59
    </em>
    1.55
    K
    1.47
    \
    1.43
    *
    1.39
    “
    1.35
    合法
    1.28
     possi
    1.27
    屋の
    1.27
    Activations Density 0.017%

    No Known Activations