© 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. 7037
    Prev
    Next
    INDEX
    Explanations

    2012 followed by an event, season, or name

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

    The neuron activates on four‐digit year tokens (e.g. “2012”).

    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
     to
    -2.06
     has
    -1.90
     by
    -1.74
     innumerable
    -1.66
     is
    -1.65
    郛
    -1.65
    erráneo
    -1.64
    鐒
    -1.63
    人的
    -1.62
    彼女は
    -1.61
    POSITIVE LOGITS
    .
    2.27
    (
    2.22
    \
    2.11
    [
    1.86
    2
    1.85
    ਃ
    1.80
    it
    1.75
    なんで
    1.67
    h
    1.66
     ceket
    1.63
    Activations Density 0.034%

    No Known Activations