© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102426
    Prev
    Next
    INDEX
    Explanations

    microphone and related audio input

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

    The neuron detects mentions of microphones, especially when discussing whether a microphone is plugged in or connected.

    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
    .”
    -2.31
     (“
    -2.23
    ”
    -2.13
    ”.
    -2.08
     —
    -2.00
    </em>
    -1.95
     “.
    -1.94
    ”,
    -1.91
     einander
    -1.87
     admittedly
    -1.80
    POSITIVE LOGITS
     succès
    2.05
     estadounid
    2.02
     endet
    2.00
    intval
    1.99
    ܆
    1.98
    饜
    1.97
    桖
    1.97
     acheter
    1.94
     fokus
    1.91
    EdgeInsets
    1.88
    Activations Density 0.007%

    No Known Activations