© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58861
    Prev
    Next
    INDEX
    Explanations

    dates and ordinal numbers

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

    The neuron strongly activates on numeric tokens—dates, quantities, and other digit‐based strings (including decimals and ordinals).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    From
    -1.80
     From
    -1.79
    ↵
    -1.62
    ministrazione
    -1.58
     daardoor
    -1.57
     by
    -1.55
    These
    -1.55
    ຜ
    -1.52
    ફ
    -1.49
    these
    -1.48
    POSITIVE LOGITS
    ation
    1.91
    -“
    1.85
    -\\
    1.80
    -”
    1.78
     étapes
    1.78
    us
    1.69
     unités
    1.66
    骉
    1.63
     œufs
    1.62
    an
    1.60
    Activations Density 0.037%

    No Known Activations