© 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. 6754
    Prev
    Next
    INDEX
    Explanations

    skeletal, aneur, armed, think

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

    The neuron activates on numeric tokens containing decimal fractions (e.g. “38.5,” “16.75,” “13.125,” 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    https
    -1.69
    mathrm
    -1.42
     from
    -1.41
    ється
    -1.39
    The
    -1.34
    rección
    -1.31
    amkeit
    -1.28
    諾
    -1.27
    uchungen
    -1.25
    ⌗
    -1.25
    POSITIVE LOGITS
     about
    1.63
     they
    1.54
     everything
    1.45
     anything
    1.31
     anywhere
    1.30
    diplom
    1.17
    </h1>
    1.14
     conoció
    1.13
    -
    1.11
     hardly
    1.10
    Activations Density 0.130%

    No Known Activations