© 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. 83653
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron detects numeric tokens that are parts of date or time expressions (e.g. month, day, or year numbers in date strings).

    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
    ᯾
    -2.05
    </em>
    -1.81
    ).
    -1.66
     wszel
    -1.66
     novidades
    -1.63
     wonderful
    -1.55
     consentimento
    -1.55
    ();
    -1.52
    (−
    -1.51
    ۠
    -1.51
    POSITIVE LOGITS
    梣
    1.68
    瑧
    1.61
    ↑↑↑
    1.49
    рите
    1.48
     tratt
    1.47
     lyk
    1.45
    Конечно
    1.45
    Plumbing
    1.43
    Thiết
    1.42
     amour
    1.41
    Activations Density 0.044%

    No Known Activations