© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98283
    Prev
    Next
    INDEX
    Explanations

    xml and code structures

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

    The neuron fires on document markup syntax, such as XML/HTML tags (e.g. “</”) and superscript tags (“sup”).

    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
     Бо
    -0.80
     before
    -0.80
     Ти
    -0.79
    rawl
    -0.77
     Speed
    -0.77
     does
    -0.75
     document
    -0.75
     Schicks
    -0.75
     court
    -0.75
     Police
    -0.75
    POSITIVE LOGITS
    ,</
    0.90
     Olin
    0.87
    不仅
    0.86
     dissimilar
    0.84
     åren
    0.84
     </
    0.84
    msub
    0.83
    HERE
    0.83
    ></
    0.81
     subscript
    0.81
    Activations Density 0.000%

    No Known Activations