© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72113
    Prev
    Next
    INDEX
    Explanations

    audio devices for listening

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

    The main thing this neuron does is detect mentions of personal audio hardware (e.g., headphones, earphones, headsets).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     it
    -1.85
     plants
    -1.41
     its
    -1.37
     of
    -1.34
     animals
    -1.32
     المسؤول
    -1.30
     nawet
    -1.26
    ApJ
    -1.23
     ciertas
    -1.23
     documents
    -1.20
    POSITIVE LOGITS
    gantian
    1.33
     设计
    1.31
    萦
    1.29
     SearchView
    1.28
    Bedankt
    1.27
    ⎓
    1.27
    DataPropertyName
    1.26
    anzug
    1.25
    Татьяна
    1.24
     pengar
    1.23
    Activations Density 0.020%

    No Known Activations