© 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. 2299
    Prev
    Next
    INDEX
    Explanations

    ".dtd" definition

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

    The neuron fires on fragments of an HTML DOCTYPE declaration URL—specifically the “XHTML 1 Transitional DTD” path (e.g. “http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd”).

    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
     blaming
    -0.69
    Vtbl
    -0.68
    لف
    -0.68
     bitter
    -0.68
     cihaz
    -0.68
     Smit
    -0.67
     Но
    -0.66
     function
    -0.66
     Москве
    -0.66
    xDB
    -0.65
    POSITIVE LOGITS
    longitude
    0.75
    énie
    0.72
     sobran
    0.67
    preorder
    0.66
    ⑶
    0.63
     LEAD
    0.63
    sepatu
    0.62
    jorie
    0.61
     กัน
    0.61
    eseen
    0.61
    Activations Density 0.084%

    No Known Activations