© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21164
    Prev
    Next
    INDEX
    Explanations

    separators and abbreviations

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

    This neuron detects segments of repeated punctuation characters (like lines of asterisks, dashes, underscores, etc.) used as visual separators or dividers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    𝐌
    -1.88
    身后的
    -1.75
    ,”
    -1.74
    Aç
    -1.64
    ➚
    -1.63
     唯美
    -1.61
    Պ
    -1.59
    masing
    -1.57
     isi
    -1.55
     チラ
    -1.55
    POSITIVE LOGITS
     find
    1.55
     for
    1.53
    .\\
    1.48
     how
    1.39
     \
    1.37
            
    1.37
     so
    1.31
    居る
    1.28
    In
    1.27
     /
    1.25
    Activations Density 0.016%

    No Known Activations