© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15839
    Prev
    Next
    INDEX
    Explanations

    communication transmit receiver codeword

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

    The neuron fires on dense technical jargon naming hardware components and signal‐processing elements—e.g. wideband/multicarrier receivers, digitizers, spectrum channels—typical of patent descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anarchist
    0.74
     homot
    0.61
     neoliberal
    0.61
     agentes
    0.60
    札
    0.60
     prothorax
    0.57
    一件
    0.57
    {\$
    0.57
     Minecraft
    0.56
     saranam
    0.56
    POSITIVE LOGITS
    transmitter
    1.05
    receiver
    1.04
     transmitter
    1.02
    Receiver
    0.99
     receiver
    0.98
    decode
    0.96
    transmit
    0.96
     Receiver
    0.95
     Transmitter
    0.94
     decoding
    0.93
    Activations Density 0.116%

    No Known Activations