© 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. 70746
    Prev
    Next
    INDEX
    Explanations

    ASP.NET followed by MVC, Core, or AJAX

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

    The neuron fires on mentions of Microsoft’s ASP .NET/.NET web‐development technologies (e.g. ASP, .NET, MVC, AJAX, Core).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     have
    -2.38
    );
    -2.22
     tecnologías
    -1.95
    琑
    -1.89
    诹
    -1.80
     It
    -1.73
    了的
    -1.70
     there
    -1.61
    ⚋
    -1.61
     never
    -1.60
    POSITIVE LOGITS
    ↵↵
    1.97
     ApiException
    1.63
    вел
    1.63
    ⢧
    1.63
     sichere
    1.60
    他们
    1.59
     yay
    1.59
    我们
    1.59
    neries
    1.56
     secretos
    1.55
    Activations Density 0.023%

    No Known Activations