© 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. 34-GEMMASCOPE-RES-131K
    7. 115587
    Prev
    Next
    INDEX
    Explanations

    PUBLIC in DOCTYPE declarations

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

    This neuron responds to the PUBLIC identifier and version numbers in DOCTYPE/DTD declarations (e.g. XML, HTML, plist DTDs).

    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
     \%)
    -0.73
    ],\
    -0.72
    ϫ
    -0.72
    ).(
    -0.69
    新幹線
    -0.68
    ريه
    -0.68
    itans
    -0.67
    bebasan
    -0.67
     :}
    -0.66
     装饰
    -0.65
    POSITIVE LOGITS
     (-
    4.25
     $-
    3.72
    (-
    3.70
     $(-
    3.28
     [-
    3.27
     "-
    3.14
    =-
    3.08
     (−
    3.00
    ="-
    2.98
    [-
    2.81
    Activations Density 0.524%

    No Known Activations