© 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. 113932
    Prev
    Next
    INDEX
    Explanations

    musical instruments and vocals

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

    The neuron detects mentions of musical instrumentation or production elements (e.g., names of instruments and related terms).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Hilsen
    -1.57
     bahkan
    -1.56
     також
    -1.51
    paisaje
    -1.47
     även
    -1.45
    reviewed
    -1.43
     גם
    -1.38
    unesse
    -1.36
     também
    -1.35
    되었습니다
    -1.35
    POSITIVE LOGITS
     over
    1.41
     назвать
    1.27
    的目光
    1.26
    当即
    1.20
    ñar
    1.14
    话音
    1.14
    レクト
    1.09
     menthe
    1.09
     куртка
    1.09
     آغاز
    1.08
    Activations Density 0.029%

    No Known Activations