© 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. 15720
    Prev
    Next
    INDEX
    Explanations

    chords and harmony

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

    The neuron detects technical musical‐theory terms—especially references to chords, chord progressions, harmonizations, arrangements, and variations.

    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
    1
    -2.56
    ’
    -1.85
    .
    -1.84
     it
    -1.76
     be
    -1.73
    6
    -1.68
    the
    -1.61
    for
    -1.61
    an
    -1.60
    s
    -1.59
    POSITIVE LOGITS
     rése
    1.78
    grupp
    1.64
    kitab
    1.63
    馓
    1.63
     oock
    1.63
    yyj
    1.62
    dekor
    1.61
    tatu
    1.60
    imiz
    1.60
     csomag
    1.55
    Activations Density 0.021%

    No Known Activations