© 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. 10-GEMMASCOPE-RES-131K
    7. 9294
    Prev
    Next
    INDEX
    Explanations

    Chesapeake, Bellevue, Sinclair, Cavaliers, Donovan, plateau

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

    This neuron detects specific proper names—especially place names and organization or team names—such as “Chesapeake Bay,” “Bellevue,” and “Cleveland Cavaliers.”

    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
    嫑
    -3.05
    这人
    -2.86
    鵙
    -2.81
    这事
    -2.80
    妧
    -2.78
    鬭
    -2.77
    千萬
    -2.75
    気付
    -2.73
    ⩖
    -2.72
    盌
    -2.70
    POSITIVE LOGITS
    ↵
    3.02
     has
    2.56
    (
    2.55
    in
    2.39
    箏
    2.38
    ).
    2.34
    .
    2.34
    up
    2.30
    然后再
    2.28
    呖
    2.28
    Activations Density 0.006%

    No Known Activations