© 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. 58222
    Prev
    Next
    INDEX
    Explanations

    levels of specific concepts

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

    The neuron primarily activates on numeric tokens (e.g., integers or decimal numbers) in the 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     nivå
    -1.78
    趵
    -1.77
     feit
    -1.74
    
    -1.72
    もあった
    -1.69
    軚
    -1.69
     orejas
    -1.68
    ってみました
    -1.67
     druge
    -1.66
    érape
    -1.66
    POSITIVE LOGITS
     If
    2.27
    <td>
    2.16
     either
    2.13
    ”,
    1.98
    ',
    1.95
    اضر
    1.81
    邹
    1.77
     a
    1.73
     When
    1.70
    蒞
    1.70
    Activations Density 0.163%

    No Known Activations