© 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. 99079
    Prev
    Next
    INDEX
    Explanations

    knights and tournaments

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

    The neuron fires on terminology evoking medieval knightly combat and tournaments.

    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
    korb
    -0.73
     Steuer
    -0.71
    ficación
    -0.70
     prokary
    -0.69
    Remarks
    -0.69
     Gehen
    -0.69
    illées
    -0.68
    uttgart
    -0.68
     sodium
    -0.67
    Mission
    -0.66
    POSITIVE LOGITS
     knight
    2.70
     knights
    2.41
     Knight
    2.09
    knight
    2.03
     Knights
    2.00
    Knight
    1.91
    Knights
    1.90
     KNIGHT
    1.83
     chivalry
    1.79
     tournaments
    1.70
    Activations Density 0.030%

    No Known Activations