© 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. 103727
    Prev
    Next
    INDEX
    Explanations

    content

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

    The neuron is detecting HTML/XML markup tokens (element tag names, brackets, and related punctuation).

    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
     กา
    -0.84
     متحده
    -0.78
    ждение
    -0.73
    INTEGR
    -0.71
    ት
    -0.71
    риан
    -0.71
    uropa
    -0.70
     Sepp
    -0.69
    ండి
    -0.69
     realización
    -0.68
    POSITIVE LOGITS
     content
    0.91
     Content
    0.88
    content
    0.84
    Content
    0.81
     header
    0.79
    Thumbnail
    0.73
     Header
    0.72
    ℎ
    0.71
    Icon
    0.71
    ヘ
    0.68
    Activations Density 0.058%

    No Known Activations