© 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. 22-GEMMASCOPE-RES-131K
    7. 12888
    Prev
    Next
    INDEX
    Explanations

    Transitional doctype declarations

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

    The neuron fires whenever it sees the word “Transitional” (and related DTD keywords like “loose”) in an HTML/XHTML DOCTYPE declaration.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.92
     this
    -1.89
    諴
    -1.81
     their
    -1.63
     Física
    -1.63
     your
    -1.61
     chapéu
    -1.58
     many
    -1.52
     when
    -1.51
    の人生
    -1.50
    POSITIVE LOGITS
    がありますが
    1.58
    を
    1.48
    があります
    1.34
    ’
    1.31
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.26
    が
    1.26
     другим
    1.25
    特别是
    1.24
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.23
    についても
    1.23
    Activations Density 0.002%

    No Known Activations