© 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. 117989
    Prev
    Next
    INDEX
    Explanations

    yacht racing and sailing

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

    The neuron detects section headings and proper‐name tokens—especially names of vessels, clubs, events, and other titled entities.

    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
     wrestlers
    -1.13
     Fußball
    -1.10
     Hockey
    -0.95
    鮎
    -0.93
    samt
    -0.93
    ataires
    -0.90
    Hockey
    -0.90
    Spel
    -0.89
     wrestler
    -0.88
    platten
    -0.87
    POSITIVE LOGITS
     crew
    1.32
     sailing
    1.28
     sail
    1.16
     fleet
    1.13
     boat
    1.13
     skipper
    1.13
     racing
    1.07
     hull
    1.03
     regata
    1.02
     sailors
    0.98
    Activations Density 0.016%

    No Known Activations