© 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. 10-GEMMASCOPE-RES-131K
    7. 65937
    Prev
    Next
    INDEX
    Explanations

    listening to music and podcasts

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

    This neuron detects mentions of listening—especially the “listen to” (and its inflected forms) construction.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    s
    -1.82
     größten
    -1.66
    Another
    -1.58
     овощи
    -1.56
    烹饪
    -1.50
    When
    -1.48
     Roughly
    -1.48
     Nonetheless
    -1.43
    In
    -1.41
     Another
    -1.36
    POSITIVE LOGITS
    り物
    1.51
    𝔗
    1.48
    👂
    1.47
     reparación
    1.46
     listened
    1.44
     intently
    1.43
    不
    1.41
     wartości
    1.40
     fortalec
    1.40
     rozdí
    1.38
    Activations Density 0.017%

    No Known Activations