© 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. 45564
    Prev
    Next
    INDEX
    Explanations

    starting phrases of articles or discussions

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

    The neuron fires on long runs of punctuation (e.g. repeated dashes or pipes) used as ASCII‐art dividers or comment separators.

    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
    /}.
    -0.76
    །
    -0.75
     professionale
    -0.73
    forKey
    -0.72
     larger
    -0.71
     lose
    -0.71
    해서
    -0.69
     terkena
    -0.69
    ثي
    -0.68
     loses
    -0.66
    POSITIVE LOGITS
     Ката
    0.75
     chế
    0.73
     ARP
    0.71
     Wonderland
    0.71
    urna
    0.71
    Diss
    0.68
    diss
    0.68
     mide
    0.68
     Diss
    0.68
     zhang
    0.67
    Activations Density 0.058%

    No Known Activations