© 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. 99422
    Prev
    Next
    INDEX
    Explanations

    golf tour events

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

    The neuron fires on named entities and terms associated with golf—especially golf players’ names, organizations, and events.

    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
    amatkan
    -0.73
     fade
    -0.72
    シェ
    -0.71
    付款
    -0.71
     instantly
    -0.70
     ERC
    -0.69
     Compulsory
    -0.69
    жден
    -0.69
    ành
    -0.68
     joked
    -0.66
    POSITIVE LOGITS
     assister
    0.93
    grow
    0.93
    usion
    0.85
     دعم
    0.84
     ومل
    0.81
     pari
    0.81
     ileg
    0.77
     grans
    0.77
     kaf
    0.77
    rán
    0.76
    Activations Density 0.015%

    No Known Activations