© 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. 34-GEMMASCOPE-RES-131K
    7. 50273
    Prev
    Next
    INDEX
    Explanations

    Korean actors and idols

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

    The neuron detects mentions of Korean pop culture proper names—especially K‐pop idols, show titles, and related celebrity 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_34/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
     disciplined
    -0.77
     ¥
    -0.72
     PRODUCTO
    -0.70
    这人
    -0.70
    Suerte
    -0.68
     STER
    -0.68
    ກ
    -0.68
    lated
    -0.68
    Attr
    -0.67
     reseña
    -0.67
    POSITIVE LOGITS
     Jessica
    0.88
     catering
    0.87
    Jessica
    0.80
     hatt
    0.77
    MBC
    0.75
    Catering
    0.74
    🩳
    0.73
     少女
    0.73
     Lagrangian
    0.73
    tiden
    0.72
    Activations Density 0.015%

    No Known Activations