© 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. 32830
    Prev
    Next
    INDEX
    Explanations

    sport and athletic disciplines

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

    The neuron fires on occurrences of “sport” or “sports,” identifying mentions of athletic activities.

    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
    belec
    -0.91
    rou
    -0.88
    轍
    -0.81
    ธรรม
    -0.77
    items
    -0.75
    靑
    -0.73
    race
    -0.72
    tada
    -0.69
    pep
    -0.68
    dure
    -0.68
    POSITIVE LOGITS
     sport
    2.83
     sports
    2.14
     deportes
    1.85
    sport
    1.80
    Sport
    1.62
     Sport
    1.59
    スポーツ
    1.55
     esportes
    1.48
    sports
    1.39
     disciplines
    1.35
    Activations Density 0.059%

    No Known Activations