© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13421
    Prev
    Next
    INDEX
    Explanations

    music theory terms like sharp, chords, scale

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

    The neuron activates on mentions of musical harmony elements—chord names, key names, and Roman-numeral chord notations in a progression.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🩰
    0.62
    atthaya
    0.60
    蜷
    0.55
    STAGE
    0.52
    avlja
    0.51
     Ballet
    0.50
    一心
    0.50
     prestazioni
    0.50
    ➩
    0.50
    utako
    0.50
    POSITIVE LOGITS
     chord
    1.04
     chords
    1.02
     chromatic
    0.99
     scale
    0.96
    Chromatic
    0.95
     Scale
    0.94
     tonic
    0.92
     minor
    0.92
     pitches
    0.89
     octave
    0.87
    Activations Density 0.149%

    No Known Activations