© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11076
    Prev
    Next
    INDEX
    Explanations

    musical pieces

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

    The neuron strongly activates on terms related to music and musical performance (e.g., “music,” “musical,” “dance,” “artistic”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quantity
    0.64
     sonore
    0.62
     Quantity
    0.58
    ತ್ತ
    0.57
    t
    0.57
    ל
    0.56
    chic
    0.55
     reserve
    0.54
     refine
    0.54
    Sup
    0.54
    POSITIVE LOGITS
    🎵
    0.78
    Brainz
    0.66
    শিক্ষা
    0.66
    اپ
    0.65
    产业
    0.64
    ஞான
    0.64
    èbre
    0.63
    ᱧ
    0.63
    雩
    0.62
     protagon
    0.61
    Activations Density 0.183%

    No Known Activations