© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8081
    Prev
    Next
    INDEX
    Explanations

    Calgary, Edmonton, Alberta

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

    The neuron fires strongly on capitalized geographic and place names (especially Canadian cities, regions, and landmarks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ліки
    -1.43
     Both
    -1.40
     estação
    -1.39
    篋
    -1.38
     preservar
    -1.38
     houve
    -1.36
     quí
    -1.34
    utare
    -1.34
     manutenção
    -1.34
     incomparable
    -1.33
    POSITIVE LOGITS
     on
    1.53
     specifica
    1.51
     frische
    1.48
     regina
    1.48
     nera
    1.40
     також
    1.37
     也
    1.37
     celebre
    1.36
    媖
    1.35
     también
    1.34
    Activations Density 0.018%

    No Known Activations