© 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. 60031
    Prev
    Next
    INDEX
    Explanations

    traceback errors with file paths

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

    the neuron detects numeric tokens (e.g. digits, version numbers, line numbers, measurements) in the text

    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
    </strong>
    -2.11
    ed
    -1.88
    '
    -1.73
    其实是
    -1.63
    也不能
    -1.58
    es
    -1.54
     of
    -1.53
    ation
    -1.51
    ys
    -1.50
    取决
    -1.50
    POSITIVE LOGITS
    ddling
    1.73
    CloseOperation
    1.70
    JsonInclude
    1.67
    出版年
    1.66
    HasIndex
    1.66
    枥
    1.65
    enchymal
    1.63
    </h5>
    1.63
    ulosa
    1.63
    leggio
    1.62
    Activations Density 0.244%

    No Known Activations