© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44049
    Prev
    Next
    INDEX
    Explanations

    linux drivers

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

    The neuron fires on technical code identifiers—especially Linux kernel paths, driver names, and related include/file tokens.

    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
     antiguas
    -1.25
     a
    -1.17
    ྄
    -1.16
    ]{
    -1.15
    ("
    -1.13
    <td>
    -1.09
    xbc
    -1.09
     sesama
    -1.09
    :"
    -1.08
     cartón
    -1.08
    POSITIVE LOGITS
    Westfalen
    1.15
     Berge
    1.09
    pedidos
    1.09
     profitable
    1.09
     espress
    1.06
     picante
    1.06
     Spirito
    1.05
    acakt
    1.03
    Ingress
    1.03
     mann
    1.03
    Activations Density 0.234%

    No Known Activations