© 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. 10-GEMMASCOPE-RES-131K
    7. 105637
    Prev
    Next
    INDEX
    Explanations

    percussion and percutaneous

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

    The neuron detects mentions of percussion (e.g. “percussion,” “percussionist,” etc.) 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
     или
    -3.08
     یا
    -2.95
    )
    -2.80
    」
    -2.66
     chiese
    -2.64
     was
    -2.53
     terremoto
    -2.48
     با
    -2.41
     داشتم
    -2.41
    !!!!!
    -2.39
    POSITIVE LOGITS
    鹛
    2.98
    狆
    2.69
    囖
    2.61
    趼
    2.47
     оранже
    2.44
    嵓
    2.22
    あります
    2.19
     gezond
    2.19
    妧
    2.17
     После
    2.16
    Activations Density 0.002%

    No Known Activations