© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78932
    Prev
    Next
    INDEX
    Explanations

    award and closing ceremonies

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    kový
    -0.78
    :>
    -0.72
    cuk
    -0.72
    voegd
    -0.68
    splan
    -0.66
    βο
    -0.66
    TableModel
    -0.66
     patience
    -0.65
    cubic
    -0.65
     Châu
    -0.65
    POSITIVE LOGITS
     ceremony
    4.34
     ceremonies
    3.17
     Ceremony
    2.58
     cérémonie
    2.38
     церемо
    2.34
     cerim
    2.17
     ceremonia
    2.14
    仪式
    1.86
     Ceremonies
    1.85
     مراسم
    1.77
    Activations Density 0.046%

    No Known Activations