© 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. 82813
    Prev
    Next
    INDEX
    Explanations

    listing of music genres

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

    The neuron is triggered by numeric tokens (digits, slashes, counts, years, and similar numeric indicators).

    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
     musicians
    -1.35
    music
    -1.26
    音樂
    -1.25
     musically
    -1.25
     музи
    -1.24
    musical
    -1.20
    Music
    -1.16
     musician
    -1.15
     musicale
    -1.13
    音乐
    -1.11
    POSITIVE LOGITS
     classical
    2.22
     jazz
    2.02
     rock
    1.85
     folk
    1.73
     Classical
    1.71
     pop
    1.66
    classical
    1.58
     Jazz
    1.55
     blues
    1.50
     gospel
    1.50
    Activations Density 0.075%

    No Known Activations