© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115635
    Prev
    Next
    INDEX
    Explanations

    Academy of Country Music

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

    The neuron is strongly activated by academic‐style metadata blocks (journal title, ISSN, volume/issue, licensing information, etc.) in a document header.

    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
     uten
    -0.79
     thanks
    -0.77
     craft
    -0.77
     pixel
    -0.76
    ıda
    -0.75
     helped
    -0.75
     dia
    -0.73
     idea
    -0.73
     caption
    -0.73
    ExternalTask
    -0.72
    POSITIVE LOGITS
     institución
    0.79
     icônes
    0.78
    voerd
    0.78
     Urgent
    0.77
    コーヒー
    0.75
    ดู
    0.74
    ुत
    0.74
     hereof
    0.74
     Detalles
    0.73
     FINISH
    0.73
    Activations Density 0.022%

    No Known Activations