© 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. 34-GEMMASCOPE-RES-131K
    7. 62768
    Prev
    Next
    INDEX
    Explanations

    musical pitch and frequency

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

    The neuron strongly activates on technical terms describing acoustic attributes—especially pitch, timbre, and tuning—used in discussions of sound or music.

    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
    więks
    -0.82
     amplitude
    -0.78
    祺
    -0.73
    svr
    -0.72
    衫
    -0.72
    케
    -0.69
    巷
    -0.69
    ractable
    -0.69
    reservation
    -0.66
     octave
    -0.66
    POSITIVE LOGITS
     Pitch
    1.14
     pitch
    1.12
    Pitch
    1.10
    pitch
    1.02
     Hz
    1.00
     pitches
    0.98
    tuning
    0.93
     tuning
    0.92
     pitched
    0.89
     tuned
    0.84
    Activations Density 0.016%

    No Known Activations