© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112494
    Prev
    Next
    INDEX
    Explanations

    foreign country names and languages

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

    The neuron activates on nationality or language identifiers (ethnonyms/demonyms) in their native forms (e.g. Italiano, Українське, Nederlandse, Française).

    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
     olika
    -2.13
    皛
    -2.08
     partag
    -2.08
     empê
    -2.03
     trám
    -2.03
     nových
    -1.97
     également
    -1.95
    腘
    -1.95
     extremamente
    -1.91
    记得
    -1.90
    POSITIVE LOGITS
    H
    2.42
    During
    2.38
    While
    2.38
    Just
    2.33
     clinica
    2.23
    Most
    2.20
    O
    2.20
    When
    2.19
    Some
    2.17
    Only
    2.16
    Activations Density 0.015%

    No Known Activations