© 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. 10-GEMMASCOPE-RES-131K
    7. 60592
    Prev
    Next
    INDEX
    Explanations

    const declarations in code

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

    This neuron fires on the “const” keyword, i.e. it detects occurrences of a constant qualifier in code.

    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
    푏
    -2.48
     nadru
    -2.45
    蕺
    -2.42
    姤
    -2.41
     Şi
    -2.38
    鷂
    -2.34
     éstas
    -2.30
    蓐
    -2.27
     Perfon
    -2.23
     mirando
    -2.22
    POSITIVE LOGITS
    \
    3.95
    ↵
    3.41
    _;
    3.33
     {
    3.27
    It
    3.23
    t
    3.08
    –
    3.00
    ”
    2.84
    什么的
    2.75
     is
    2.73
    Activations Density 0.023%

    No Known Activations