© 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. 90322
    Prev
    Next
    INDEX
    Explanations

    marshalling bytes or buffers

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

    The neuron fires on code tokens referring to raw binary data—especially “byte”/“bytes” types, byte-array literals (b'…'), and related buffer operations.

    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
    even
    -1.60
    J
    -1.46
    who
    -1.33
    c
    -1.33
    C
    -1.30
    what
    -1.30
    lıkla
    -1.27
    while
    -1.27
    selben
    -1.26
    if
    -1.25
    POSITIVE LOGITS
     Cuando
    1.47
    <bos>
    1.41
    ámica
    1.35
    TacToe
    1.30
    ficulties
    1.27
     ||
    
    1.23
    niť
    1.23
     to
    1.22
    vedades
    1.20
    metology
    1.20
    Activations Density 0.037%

    No Known Activations