© 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. 22-GEMMASCOPE-RES-131K
    7. 36320
    Prev
    Next
    INDEX
    Explanations

    media playback devices and features

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

    The main thing this neuron does is find mentions of audio/media playback or connectivity features (e.g. Bluetooth, speaker, iPod/MP3 input, streaming).

    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
     vinaigre
    -1.31
     telewiz
    -1.26
     cuya
    -1.23
    gucigalpa
    -1.13
    }:=\
    -1.09
    ǡ
    -1.09
     kits
    -1.09
    也不知道
    -1.08
     Sobald
    -1.07
    pensione
    -1.07
    POSITIVE LOGITS
     उपलब्ध
    1.23
     your
    1.23
     möjlighet
    1.10
    お疲れ
    1.07
     keuze
    1.06
     khiển
    1.06
    ご予約
    1.04
     mogelijkheid
    1.02
     you
    1.02
     capability
    1.02
    Activations Density 0.023%

    No Known Activations