© 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. 34-GEMMASCOPE-RES-131K
    4. 116019
    Prev
    Next
    INDEX
    Explanations

    audio and playback systems

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

    This neuron detects mentions of audio-related iOS API classes and functions (e.g. AVAudioRecorder, AVAudioSession, audio recording 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
     Сте
    -0.81
    Whis
    -0.73
    ቀ
    -0.73
    bber
    -0.70
     tấm
    -0.69
     financiamiento
    -0.69
     dominate
    -0.69
    Cameras
    -0.68
    вае
    -0.68
     oint
    -0.67
    POSITIVE LOGITS
     AVA
    1.03
    AUG
    0.89
     AUG
    0.89
    Audio
    0.86
     Audio
    0.79
    ʋ
    0.76
    veau
    0.75
    Player
    0.74
     Diary
    0.73
    CBT
    0.73
    Activations Density 0.021%

    No Known Activations