© 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. 38690
    Prev
    Next
    INDEX
    Explanations

    pole position

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

    The neuron detects mentions of motor racing events and their associated race details, especially “Grand Prix”–style races.

    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
    obio
    -0.79
    arai
    -0.79
     Ах
    -0.79
     soos
    -0.79
    DECIMAL
    -0.78
     granat
    -0.76
     Martinez
    -0.75
    compareTo
    -0.75
     Cava
    -0.73
     Voyage
    -0.72
    POSITIVE LOGITS
     pole
    2.31
     poles
    1.82
     qualifying
    1.81
    pole
    1.73
     qualify
    1.71
     Pole
    1.66
    Pole
    1.65
     podium
    1.58
     квали
    1.52
     qualification
    1.46
    Activations Density 0.027%

    No Known Activations