© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111891
    Prev
    Next
    INDEX
    Explanations

    page keywords like Page_Load

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

    the word "page" in programming code contexts, particularly in web development frameworks like JSP, ASP.NET, and page directives.

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

    The neuron activates strongly on the token “page” (and its variants) in code or markup directives.

    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
     primeiros
    -1.84
     today
    -1.55
     you
    -1.52
     seguintes
    -1.48
     estructura
    -1.47
     celé
    -1.46
     muitos
    -1.38
     primeiras
    -1.36
     the
    -1.34
     said
    -1.30
    POSITIVE LOGITS
    "
    2.34
    <bos>
    2.03
    1.53
     ||

    1.45
    There
    1.38
    ）、
    1.34
    If
    1.34
    </td>
    1.34
     jego
    1.33
     &&

    1.33
    Activations Density 0.002%
    No Known Activations