© 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. 10-GEMMASCOPE-RES-131K
    7. 130884
    Prev
    Next
    INDEX
    Explanations

    classical music compositions

    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_10/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
     who
    -2.16
    还得
    -1.88
     Hift
    -1.72
    zembro
    -1.65
     réessayer
    -1.64
     optimizar
    -1.58
     enliven
    -1.56
     fenô
    -1.55
     botão
    -1.55
    で見る
    -1.45
    POSITIVE LOGITS
     on
    2.11
     not
    2.05
     by
    2.00
     "
    1.85
     of
    1.83
     for
    1.80
     more
    1.63
     as
    1.60
     so
    1.51
    .
    1.51
    Activations Density 0.040%

    No Known Activations