© 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. 103670
    Prev
    Next
    INDEX
    Explanations

    Xilinx FPGA terms

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

    The neuron is specifically detecting mentions of “Xilinx” (and its parts like “Xil,” “ilinx,” etc.).

    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
     Robson
    -0.77
     Egon
    -0.75
    Punjab
    -0.75
     Punjab
    -0.71
    км
    -0.70
     Fuzz
    -0.70
    ) 
    -0.69
     Odds
    -0.69
     strada
    -0.68
     Lans
    -0.68
    POSITIVE LOGITS
    vitis
    1.02
     FPGA
    1.02
    FPGA
    0.98
    xil
    0.88
    hls
    0.84
     fp
    0.84
     zyn
    0.83
    zyn
    0.82
     Viv
    0.81
     Spartan
    0.80
    Activations Density 0.036%

    No Known Activations