© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76509
    Prev
    Next
    INDEX
    Explanations

    and musical instruments

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

    The neuron fires on numeric metadata—especially numbers indicating durations, opus/catalog numbers, or instrumentation counts—within lists of musical compositions.

    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
     музи
    -0.88
     melodies
    -0.88
     instrument
    -0.83
     musicales
    -0.82
     Musiker
    -0.82
    opoulos
    -0.81
     music
    -0.81
     музыку
    -0.80
     Music
    -0.79
     песен
    -0.78
    POSITIVE LOGITS
     female
    1.20
     two
    1.02
     strings
    0.96
     algodão
    0.91
    electronics
    0.91
     Publikum
    0.90
    computers
    0.88
     narrator
    0.86
     horns
    0.86
     céu
    0.86
    Activations Density 0.013%

    No Known Activations