© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98630
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

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

    The neuron fires on numeric literal characters—especially hexadecimal digits—within code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    lapis
    -1.49
    来看看
    -1.45
    一起来
    -1.45
    㐂
    -1.43
     paraíso
    -1.41
    
    -1.41
    つづく
    -1.41
    汽車
    -1.40
     芋
    -1.39
    經典
    -1.38
    POSITIVE LOGITS
    就算
    1.66
    6
    1.50
     той
    1.48
    ">//
    1.48
     \
    1.46
    {
    1.41
    部队
    1.41
    StoryboardSegue
    1.40
    ↵
    1.34
    ícias
    1.34
    Activations Density 0.026%

    No Known Activations