© 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. 54307
    Prev
    Next
    INDEX
    Explanations

    music and soundtracks

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

    The neuron fires on tokens from structured metadata fields (e.g. infobox keys and their values such as “sound”, “producer”, “music”, numeric fields, etc.).

    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
    entlichen
    -0.77
    elles
    -0.72
    autorelease
    -0.71
    
    -0.71
     ogrod
    -0.71
    ENDENT
    -0.71
     mengurangi
    -0.70
    FLD
    -0.69
     membaca
    -0.69
     香
    -0.69
    POSITIVE LOGITS
     track
    1.27
     instrumental
    1.20
     tracks
    1.18
     OST
    1.16
     ambience
    1.16
     composer
    1.15
     composers
    1.15
    track
    1.14
     piano
    1.10
     boss
    1.09
    Activations Density 0.017%

    No Known Activations