© 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. 83732
    Prev
    Next
    INDEX
    Explanations

    years and dates

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

    The neuron fires on numeric tokens—especially standalone numbers (including integers and decimals) in tables or data listings.

    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
     of
    -2.28
    也
    -1.91
     kazi
    -1.84
    .");
    -1.81
    This
    -1.80
    ｅ
    -1.75
     uruguay
    -1.74
    .”
    -1.70
    。”
    -1.69
     fei
    -1.69
    POSITIVE LOGITS
     glistening
    2.09
     wither
    2.02
     большого
    1.82
     glittering
    1.79
     tendrá
    1.77
     forlorn
    1.74
     languid
    1.71
     unspeakable
    1.70
    因为他
    1.68
     teeming
    1.68
    Activations Density 0.064%

    No Known Activations