© 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. 10-GEMMASCOPE-RES-131K
    7. 113823
    Prev
    Next
    INDEX
    Explanations

    doctype html public

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

    the DOCTYPE declaration and character encoding specifications in HTML documents.

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

    The neuron flags HTML/XML declaration tokens—especially attribute names and values like PUBLIC, EN, charset, and lang in DOCTYPE and meta tags.

    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
     
    -1.90
     conseguido
    -1.63
    when
    -1.53
     adquirido
    -1.52
     if
    -1.52
     pagado
    -1.52
    da
    -1.46
     comprado
    -1.45
    ভা
    -1.38
     еще
    -1.37
    POSITIVE LOGITS
     of
    2.56
    ,
    2.16
    沨
    1.96
    8
    1.81
     پروفایل
    1.52
     ۱۶
    1.49
    倧
    1.49
     remainder
    1.49
    losures
    1.48
    ໊
    1.44
    Activations Density 0.027%

    No Known Activations