© 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. 107420
    Prev
    Next
    INDEX
    Explanations

    Saint- or San- prefixes

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

    This neuron detects hyphenated place names beginning with “Saint-.”

    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
     prosthetic
    -0.77
    슬
    -0.75
     by
    -0.73
    瀨
    -0.73
    edition
    -0.72
    Doi
    -0.72
    enguins
    -0.72
     simply
    -0.71
    каде
    -0.70
    Lecture
    -0.67
    POSITIVE LOGITS
     クッキー
    0.88
     Roch
    0.87
     Jesus
    0.85
    ाषा
    0.81
     Mathis
    0.79
    ピュー
    0.79
     funzion
    0.78
     iner
    0.77
     precluded
    0.77
    Vamos
    0.76
    Activations Density 0.025%

    No Known Activations