© 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. 43258
    Prev
    Next
    INDEX
    Explanations

    cuda technical memory

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

    The neuron strongly activates on the letter sequences “aus” (as in Auscultated/Ausweichen) and “cuda” (the CUDA library name).

    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
     
    -4.47
     "
    -3.41
    "
    -2.94
    ↵
    -2.86
    .
    -2.77
    ’
    -2.77
     -
    -2.75
    て
    -2.70
     "'
    -2.70
     ''
    -2.69
    POSITIVE LOGITS
    鉏
    2.97
    諼
    2.94
    
    2.92
     BIEN
    2.86
     всѣ
    2.80
     VOUS
    2.75
    龑
    2.72
     内衣
    2.72
    盦
    2.67
     GRATU
    2.66
    Activations Density 0.001%

    No Known Activations