© 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. 34-GEMMASCOPE-RES-131K
    7. 54226
    Prev
    Next
    INDEX
    Explanations

    action potentials, voltage-gated channels

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

    The neuron primarily activates on numeric values and measurements in scientific/medical texts, especially when appearing in tables, data, or statistics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on tokens that are part of structural or numeric markers—especially digits, hyphens, and other formatting symbols used for numbering and sectioning.

    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
    cemos
    -0.85
     ơi
    -0.78
     we
    -0.78
    jemah
    -0.75
     fået
    -0.75
     Biomed
    -0.73
    верен
    -0.73
    íns
    -0.73
    jeros
    -0.72
     Tradu
    -0.72
    POSITIVE LOGITS
    ologic
    0.88
    staus
    0.79
    erías
    0.78
     recomendación
    0.77
    мл
    0.77
    :][
    0.76
     Baroness
    0.75
    quarie
    0.75
     Lithuania
    0.75
     tweeting
    0.75
    Activations Density 0.009%

    No Known Activations