© 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. 22-GEMMASCOPE-RES-131K
    7. 16739
    Prev
    Next
    INDEX
    Explanations

    program else blocks

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

    The neuron is detecting numeric literals (digits and numbers) in code or text.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     berken
    -1.24
     that
    -1.22
     navegación
    -1.11
     of
    -1.03
    だね
    -0.96
     軒
    -0.96
    dür
    -0.95
     VOOR
    -0.95
     desfile
    -0.95
     mengunjungi
    -0.95
    POSITIVE LOGITS
     else
    1.28
    else
    1.27
    给我们
    1.05
     же
    1.05
    もとも
    0.97
     некоторых
    0.96
    黑的
    0.96
    čenje
    0.94
    ora
    0.94
     ciertas
    0.93
    Activations Density 0.001%

    No Known Activations