© 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. 2025
    Prev
    Next
    INDEX
    Explanations

    musical notes and chords

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

    This neuron primarily detects musical chord symbols (e.g., “Gm,” “Eb,” “Bb,” “F,” “Cm”) in song or sheet-music notation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    mrc
    -0.91
     that
    -0.88
     ofici
    -0.83
    pinyin
    -0.82
    uresh
    -0.80
     oyuncu
    -0.80
    stringBuffer
    -0.80
     if
    -0.78
     Deixe
    -0.77
     espectadores
    -0.76
    POSITIVE LOGITS
     Dm
    0.96
     sult
    0.90
     Bb
    0.88
     Dominant
    0.87
     Gm
    0.86
     alpes
    0.85
     recognises
    0.84
     Slick
    0.82
    Repeat
    0.82
     repeat
    0.81
    Activations Density 0.014%

    No Known Activations