© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109380
    Prev
    Next
    INDEX
    Explanations

    CPU and processor names

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

    The neuron fires on hardware‐ and CPU‐specification details, especially model names and numeric specs.

    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
    wapV
    -0.72
    angerie
    -0.72
    ureau
    -0.71
     consentimento
    -0.71
     pescoço
    -0.70
    щі
    -0.69
    epam
    -0.69
    trz
    -0.69
    ArrowToggle
    -0.69
    litt
    -0.69
    POSITIVE LOGITS
     processor
    1.22
     processors
    1.13
     CPU
    1.12
    Processor
    1.00
    cpu
    0.97
    processor
    0.94
     cpu
    0.89
     Processor
    0.84
    CPU
    0.84
    Dual
    0.84
    Activations Density 0.041%

    No Known Activations