© 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. 65892
    Prev
    Next
    INDEX
    Explanations

    sprint canoer or long-distance runner

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

    The neuron flags mentions of athletic event specializations—terms like “long-distance runner,” “sprint canoeer,” “track,” etc.

    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
    icator
    -0.79
    undet
    -0.77
    级
    -0.74
    toMatch
    -0.74
     fidu
    -0.74
    localtime
    -0.73
    setzungen
    -0.72
    ativeness
    -0.70
    StreetMap
    -0.70
     Etter
    -0.70
    POSITIVE LOGITS
     sprint
    2.23
     distance
    2.03
     sprints
    1.88
     marathon
    1.74
     Sprint
    1.73
     spr
    1.68
     sprinter
    1.63
     shorter
    1.63
     distances
    1.61
    marathon
    1.52
    Activations Density 0.047%

    No Known Activations