© 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. 64337
    Prev
    Next
    INDEX
    Explanations

    academic paper citations

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

    The neuron is primarily sensitive to any token containing numeric digits (e.g. class names or identifiers with numbers, sheet/range labels, reference IDs, etc.).

    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
    فح
    -0.86
    寤
    -0.85
     shortly
    -0.85
    鶻
    -0.84
    ندق
    -0.79
    ném
    -0.79
     and
    -0.78
    ография
    -0.77
    附近的
    -0.77
     both
    -0.77
    POSITIVE LOGITS
     aktiviert
    0.88
    taan
    0.88
    cc
    0.84
    了一句
    0.82
     reiz
    0.81
     istore
    0.81
    ológ
    0.78
     بير
    0.77
     ADDITIONAL
    0.77
    不禁
    0.77
    Activations Density 0.073%

    No Known Activations