© 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. 75987
    Prev
    Next
    INDEX
    Explanations

    songs, singing, music

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

    The main thing this neuron does is detect references to songs or singing (e.g. song, sung, tune).

    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
    ISODE
    -0.82
    ilibr
    -0.82
    ornis
    -0.78
     savait
    -0.77
    correspond
    -0.76
    Mercado
    -0.73
     lettre
    -0.73
    âte
    -0.73
     violência
    -0.73
    の音
    -0.72
    POSITIVE LOGITS
     singing
    3.88
     sung
    3.22
     song
    3.20
     songs
    3.05
     sings
    2.83
     sing
    2.70
    singing
    2.66
     sang
    2.61
     singers
    2.48
     lyrics
    2.38
    Activations Density 0.053%

    No Known Activations