© 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. 98437
    Prev
    Next
    INDEX
    Explanations

    audio signal and voices

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

    The neuron detects mentions of audio channel specifications, especially a numeric channel count paired with “channel audio” or related terms.

    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
    iforms
    -0.71
    𝖨
    -0.71
    ברו
    -0.71
    gnan
    -0.70
    วจ
    -0.70
    sensi
    -0.69
     skup
    -0.69
    ่ม
    -0.68
     heaped
    -0.68
     Contempor
    -0.67
    POSITIVE LOGITS
     surround
    2.52
     Surround
    1.95
     Dolby
    1.87
     surrounds
    1.72
     DTS
    1.42
     Atmos
    1.34
    Dol
    1.27
    Sur
    1.27
    sur
    1.21
     sound
    1.18
    Activations Density 0.015%

    No Known Activations