© 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. 34-GEMMASCOPE-RES-131K
    7. 91934
    Prev
    Next
    INDEX
    Explanations

    Sonos players and Spotify

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

    This neuron fires on proper nouns and technical acronyms (e.g. brand or technology names).

    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
    干し
    -0.75
     Ordnung
    -0.74
     skjer
    -0.73
     tet
    -0.73
     걸
    -0.72
    འི་
    -0.68
     footage
    -0.66
    遗址
    -0.66
     liest
    -0.65
    ibles
    -0.65
    POSITIVE LOGITS
     Sonos
    1.11
    Players
    1.02
    PLAYER
    0.93
    Spotify
    0.90
     rooms
    0.90
     players
    0.89
     Spotify
    0.89
     Players
    0.89
    player
    0.86
    Zones
    0.85
    Activations Density 0.012%

    No Known Activations