© 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. 110657
    Prev
    Next
    INDEX
    Explanations

    South Korean

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

    The main thing this neuron does is detect proper‐noun references and named entities specifically tied to South Korea (e.g. Korean organizations, companies, sports leagues, and locations).

    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
     kapturem
    -1.10
     telinga
    -1.07
    letzt
    -1.07
    hichever
    -1.05
    ουμε
    -1.05
     siempre
    -1.05
     excès
    -1.04
     gesunde
    -1.02
     always
    -1.01
     таком
    -1.01
    POSITIVE LOGITS
     will
    1.52
     their
    1.49
     there
    1.31
    appendTo
    1.13
     what
    1.02
     ПК
    1.02
    其
    1.02
    Eksterne
    1.00
     prepared
    1.00
     are
    0.96
    Activations Density 0.189%

    No Known Activations