© 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. 34787
    Prev
    Next
    INDEX
    Explanations

    xml, Mutations, federal

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

    The neuron fires on mentions of “libxml2” (and its components “lib,” “xml,” and “2”) and on numeric/version tokens (e.g. version numbers, large digit sequences) in code or license headers.

    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
    Ṛ
    -0.80
     Wojciech
    -0.77
     При
    -0.76
    ⓗ
    -0.76
    bm
    -0.74
     Estonia
    -0.72
     Tartu
    -0.70
    øm
    -0.70
     numerically
    -0.69
     secs
    -0.68
    POSITIVE LOGITS
     xml
    0.90
     XML
    0.88
     Roswell
    0.84
    manas
    0.84
    zeiro
    0.83
    voyer
    0.79
     BAD
    0.77
    balah
    0.77
     黄色
    0.75
     thái
    0.75
    Activations Density 0.028%

    No Known Activations