© 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. 34-GEMMASCOPE-RES-131K
    7. 92049
    Prev
    Next
    INDEX
    Explanations

    Meteor Garden Taiwanese dramas

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

    This neuron activates on mentions of Korean-related proper nouns and phrases—especially the word “Korean” or “South Korean” in names and titles.

    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
    uição
    -0.78
     molta
    -0.77
    laints
    -0.73
     Magh
    -0.71
    libft
    -0.71
     regio
    -0.71
    abases
    -0.70
    ImageContext
    -0.69
     Dede
    -0.69
    vscode
    -0.69
    POSITIVE LOGITS
     meteor
    1.04
     Taiwanese
    0.91
     台湾
    0.85
     Prince
    0.85
     Meteor
    0.84
    meteor
    0.82
    Customization
    0.81
     Taiwan
    0.79
    ेंट
    0.77
    Meteor
    0.75
    Activations Density 0.022%

    No Known Activations