© 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. 9016
    Prev
    Next
    INDEX
    Explanations

    nationalities and professions

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

    This neuron fires on country or nationality names (demonyms) and related geographic terms.

    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
     from
    -1.94
    亖
    -1.89
     as
    -1.89
     or
    -1.84
    ="
    -1.67
     such
    -1.67
     like
    -1.63
     first
    -1.62
     then
    -1.62
    遹
    -1.60
    POSITIVE LOGITS
    将他
    1.80
    低声
    1.67
    将她
    1.63
    hibitions
    1.61
    },
    1.48
    倏
    1.46
    genicity
    1.45
     chiar
    1.43
    骤
    1.43
    OS
    1.38
    Activations Density 0.470%

    No Known Activations