© 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. 10-GEMMASCOPE-RES-131K
    7. 19934
    Prev
    Next
    INDEX
    Explanations

    place name components

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

    The neuron fires on geographic proper names—particularly place names like counties, towns, and other location names.

    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
     these
    -1.49
     atleast
    -1.48
     communes
    -1.48
     blanches
    -1.48
     抽象
    -1.47
     くん
    -1.45
    Zubereitung
    -1.45
     {}\
    -1.45
    フラン
    -1.45
     accla
    -1.44
    POSITIVE LOGITS
    '
    2.17
    los
    2.02
    us
    1.77
    $
    1.74
    in
    1.73
    his
    1.73
    en
    1.66
    </h1>
    1.61
    they
    1.61
    olate
    1.60
    Activations Density 0.564%

    No Known Activations