© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43448
    Prev
    Next
    INDEX
    Explanations

    file formats, document types

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

    The neuron activates strongly on musical chord symbols (e.g. C, Am, Gm, Eb, Bb, F) appearing in song or sheet-music text.

    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
     rám
    -1.66
     fidé
    -1.65
     eenvou
    -1.64
     Reſ
    -1.64
     moeili
    -1.63
    bagian
    -1.62
    mga
    -1.62
     réve
    -1.60
     interak
    -1.59
     jednej
    -1.56
    POSITIVE LOGITS
     not
    1.89
     so
    1.77
     get
    1.63
     did
    1.59
     after
    1.59
     Not
    1.56
     still
    1.53
     There
    1.53
     does
    1.50
     не
    1.48
    Activations Density 0.535%

    No Known Activations