© 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. 34-GEMMASCOPE-RES-131K
    7. 106441
    Prev
    Next
    INDEX
    Explanations

    compilers and compilation tools

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

    The neuron activates on numeric tokens (i.e. standalone numbers or version/build codes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Finns
    -0.73
    quants
    -0.72
    asier
    -0.72
    tration
    -0.71
    ovali
    -0.71
     grained
    -0.69
    Running
    -0.69
    Scripture
    -0.69
    GLFW
    -0.68
    orige
    -0.67
    POSITIVE LOGITS
     compiler
    3.20
     compilers
    2.41
    compiler
    2.41
     Compiler
    2.30
    Compiler
    2.16
    编译
    2.02
     gcc
    1.91
     GCC
    1.85
    GCC
    1.58
    gcc
    1.51
    Activations Density 0.352%

    No Known Activations