© 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. 75634
    Prev
    Next
    INDEX
    Explanations

    tokens following specific punctuation or abbreviations

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

    This neuron detects uppercase token names (especially arithmetic operator tokens like PLUS, MINUS, TIMES, DIVIDE) listed in grammar precedence declarations.

    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
    โท
    -0.75
     Trocken
    -0.72
    ocrats
    -0.72
    最悪
    -0.71
     boredom
    -0.71
    assadors
    -0.69
     Matthew
    -0.68
    要不是
    -0.68
     trưởng
    -0.67
    zels
    -0.67
    POSITIVE LOGITS
    getText
    0.93
    mle
    0.83
    分鐘
    0.82
    ﷺ
    0.82
    ровка
    0.80
     WS
    0.79
     trăng
    0.78
     RULE
    0.76
    ΗΣ
    0.75
     Heist
    0.75
    Activations Density 0.006%

    No Known Activations