© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62587
    Prev
    Next
    INDEX
    Explanations

    viral songs

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

    The neuron strongly activates on the split‐up tokens of the viral song title “Gangnam Style.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     greatly
    -0.80
     fear
    -0.77
     two
    -0.75
     designed
    -0.75
     change
    -0.75
     used
    -0.75
    ဉ
    -0.75
    Tensi
    -0.75
     for
    -0.74
     as
    -0.74
    POSITIVE LOGITS
     viral
    1.40
     craze
    1.14
     Viral
    1.09
    Viral
    1.01
    viral
    1.01
     fad
    0.99
     PSY
    0.96
     paro
    0.94
     hysteria
    0.93
     certitude
    0.90
    Activations Density 0.037%

    No Known Activations