© 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. 73604
    Prev
    Next
    INDEX
    Explanations

    Edmonton Alberta Oilers

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

    The neuron strongly activates on tokens that are part of multi-word geographical place names (e.g. “Edmonton Metropolitan Region”).

    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
    keletal
    -0.71
    絡
    -0.70
    ＝＝
    -0.69
     DELLE
    -0.67
     Chandigarh
    -0.67
     sami
    -0.67
     Denison
    -0.67
    cleros
    -0.67
     Guanajuato
    -0.66
    cotch
    -0.66
    POSITIVE LOGITS
     Edmonton
    1.82
    Edmonton
    1.61
     Alberta
    1.51
    Alberta
    1.38
     Oilers
    1.06
    ULING
    0.85
     Jasper
    0.84
     Botanic
    0.81
     Lakeland
    0.75
    monton
    0.75
    Activations Density 0.029%

    No Known Activations