© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2854
    Prev
    Next
    INDEX
    Explanations

    ASP.NET Core middleware

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

    The neuron fires on ASP .NET Core–related C# code and terminology—e.g. class names, middleware pipeline types, namespaces, and methods from an ASP .NET Core context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     राम
    -0.83
    ㄠ
    -0.75
    tomation
    -0.75
     terrains
    -0.75
    小花
    -0.74
     ésta
    -0.73
     pensent
    -0.73
     dilatation
    -0.70
    Efficacy
    -0.70
     fandom
    -0.69
    POSITIVE LOGITS
     konkuren
    0.84
     Revere
    0.79
     AspNetCore
    0.79
    留
    0.79
    atr
    0.78
    ************
    0.78
    可
    0.77
    ழ்
    0.77
    gcd
    0.77
    Massachusetts
    0.74
    Activations Density 0.042%

    No Known Activations