© 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. 22-GEMMASCOPE-RES-131K
    7. 38799
    Prev
    Next
    INDEX
    Explanations

    graphics and programming buffers

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

    This neuron fires on code tokens referring to buffer objects or buffer‐related API calls (e.g. “glBindBuffer,” “Buffer,” “vbo,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    THE
    -1.20
     >
    -1.14
    if
    -1.05
     would
    -1.03
     fighter
    -1.02
    y
    -0.97
    while
    -0.97
     =
    -0.97
     like
    -0.95
     wenigstens
    -0.94
    POSITIVE LOGITS
    unut
    1.13
    euvres
    1.12
    ០
    1.11
    ים
    1.11
    ємо
    1.09
    カタ
    1.09
    segno
    1.09
    ως
    1.09
    ïde
    1.07
    اديم
    1.07
    Activations Density 0.005%

    No Known Activations