© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19985
    Prev
    Next
    INDEX
    Explanations

    quotation marks, parentheses, and names

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

    The neuron fires on tokens representing numeric literals (integers or decimals).

    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
    脔
    -1.88
    蛱
    -1.70
     ("%
    -1.66
    sandalia
    -1.64
     côn
    -1.59
    蚡
    -1.59
    糴
    -1.59
    菒
    -1.58
    ⚣
    -1.57
     paño
    -1.56
    POSITIVE LOGITS
     any
    1.95
     at
    1.95
     had
    1.88
     makes
    1.82
     may
    1.73
     ALL
    1.67
     additional
    1.66
     gives
    1.65
     sufficient
    1.64
     There
    1.63
    Activations Density 0.006%

    No Known Activations