© 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. 69568
    Prev
    Next
    INDEX
    Explanations

    Cape Verdean, Azerori, Busan, County Sheriff

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

    The neuron responds strongly to capitalized named entities (people’s surnames, place names, species or organization 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
    {
    -2.72
     spezi
    -1.77
    
    -1.77
    for
    -1.71
    肫
    -1.69
    自从
    -1.68
    孱
    -1.66
    ).
    -1.65
    Elaboración
    -1.65
     QUARTER
    -1.61
    POSITIVE LOGITS
    <bos>
    1.98
    夲
    1.95
    靂
    1.83
     ähnliche
    1.77
    eſ
    1.74
     zahlreiche
    1.74
     he
    1.74
     who
    1.70
    ’
    1.67
    댔
    1.67
    Activations Density 0.003%

    No Known Activations