© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102776
    Prev
    Next
    INDEX
    Explanations

    web MVC

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

    the ".web" token in namespaces or package paths, particularly in Spring Framework and web development contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of “Web” or “web” in framework names, package paths, or import/config labels (e.g. Spring WebFlux, web.bind.annotation, spring.web).

    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
    ’
    -2.50
     a
    -1.95
     of
    -1.80
    }\}$
    -1.77
     (‘
    -1.73
    已经
    -1.64
    或
    -1.59
    «,
    -1.59
    大多
    -1.56
     puas
    -1.56
    POSITIVE LOGITS
    Greece
    1.43
     maravillosa
    1.41
    啻
    1.38
    狃
    1.38
    鴞
    1.38
    flä
    1.37
    负担
    1.37
    kör
    1.36
    iç
    1.34
    諄
    1.34
    Activations Density 0.003%

    No Known Activations