© 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. 10-GEMMASCOPE-RES-131K
    7. 83891
    Prev
    Next
    INDEX
    Explanations

    composers and artists

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

    The neuron fires on classical‐music terminology—especially composer names, key signatures, instruments, and movement or suite titles.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     of
    -1.63
     más
    -1.63
     –
    -1.60
    ;
    -1.52
    0
    -1.50
     \
    -1.50
     they
    -1.43
    –
    -1.41
    ates
    -1.39
     |
    -1.38
    POSITIVE LOGITS
    Bakgrunns
    1.45
     込
    1.42
     Allí
    1.41
    咝
    1.38
     fotografías
    1.35
    nitten
    1.34
    towych
    1.34
    鶺
    1.33
     thunderbolt
    1.33
     icône
    1.33
    Activations Density 0.017%

    No Known Activations