© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10642
    Prev
    Next
    INDEX
    Explanations

    multiplexing and multiplexers

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

    The neuron activates on mentions of “multiplex” (and related abbreviations like MUX/DEMUX) in communications contexts.

    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
     навіть
    -1.99
    en
    -1.95
    P
    -1.88
     seperti
    -1.84
     sería
    -1.82
     paramount
    -1.81
    ↵↵
    -1.80
    '/',
    -1.78
    或者
    -1.75
     Regardless
    -1.63
    POSITIVE LOGITS
    鉨
    2.47
    utiva
    2.41
    鉝
    2.33
    妡
    2.22
    蟥
    2.20
    CONSIN
    2.14
    cuado
    2.13
    ICIONES
    2.09
    AMPLES
    2.05
    。
    2.05
    Activations Density 0.013%

    No Known Activations