© 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. 10-GEMMASCOPE-RES-131K
    4. 39158
    Prev
    Next
    INDEX
    Explanations

    cuda related terms

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

    The neuron fires on code tokens referring to NVIDIA’s CUDA ecosystem (e.g. “cuda,” “cudnn,” versioned CUDA base images, and related API calls).

    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
     This
    -2.75
    m
    -2.66
     That
    -2.55
    спомина
    -2.53
     According
    -2.50
    泺
    -2.42
     While
    -2.36
     With
    -2.33
    ’
    -2.28
    </h3>
    -2.19
    POSITIVE LOGITS
    に
    2.20
     â
    2.16
    蟥
    2.06
    UDO
    2.05
    utusan
    2.05
    扪
    2.00
    鱚
    2.00
    thschild
    2.00
     très
    1.99
    龉
    1.99
    Activations Density 0.003%

    No Known Activations