© 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. 81109
    Prev
    Next
    INDEX
    Explanations

    html tags and xml

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

    The neuron is primarily triggered by HTML/XML structural markup (e.g. tag delimiters like “<…>”, “</…>”, and comment markers “<!-- … -->”).

    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
    ług
    -0.90
    もない
    -0.82
    kN
    -0.82
    пущен
    -0.79
     Unterstüt
    -0.79
     tsk
    -0.77
    tk
    -0.76
    х
    -0.75
     USB
    -0.75
     flesta
    -0.75
    POSITIVE LOGITS
     daugiau
    1.02
     penutup
    0.94
    <?
    0.90
    ebly
    0.89
     reikia
    0.87
     attempting
    0.87
     atrás
    0.86
    Zá
    0.85
     trying
    0.82
    뒤
    0.82
    Activations Density 0.006%

    No Known Activations