© 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. 129717
    Prev
    Next
    INDEX
    Explanations

    dac and ac prefixes

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

    The neuron detects mentions of “digital-to-analog converters” (the term “analog converter” and its acronym “DAC”).

    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
    งิน
    -3.78
    囖
    -3.17
     ſie
    -3.13
    颼
    -3.09
    过后
    -2.97
    
    -2.94
     leaſt
    -2.92
    瞜
    -2.91
     gustado
    -2.88
     That
    -2.84
    POSITIVE LOGITS
    '
    4.19
    A
    4.06
    In
    3.08
    D
    3.00
    [
    2.78
    \
    2.72
    on
    2.69
    V
    2.69
    and
    2.67
    J
    2.64
    Activations Density 0.004%

    No Known Activations