© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32230
    Prev
    Next
    INDEX
    Explanations

    Formula 1, Benetton

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

    The neuron detects tokens describing Formula One Grand Prix events (race names, dates, venues, and race-specific details).

    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
    Dispatcher
    -0.78
    TPM
    -0.76
    Reaper
    -0.76
    ceno
    -0.76
     peccato
    -0.75
     Grado
    -0.75
     querían
    -0.75
    🪛
    -0.75
    ࣭
    -0.75
    ientemente
    -0.74
    POSITIVE LOGITS
     QUAL
    0.94
     DESIGN
    0.90
    QUAL
    0.87
     Banerjee
    0.85
    coring
    0.81
    qual
    0.79
     FAIL
    0.77
     Formule
    0.75
    ativos
    0.75
    esign
    0.73
    Activations Density 0.024%

    No Known Activations