© 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. 22-GEMMASCOPE-RES-131K
    7. 64517
    Prev
    Next
    INDEX
    Explanations

    periods until

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

    The neuron fires strongly on numeric expressions of time or duration (e.g. “few hours,” “30 minutes,” “decades,” etc.).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    涅
    -0.84
     sobald
    -0.84
     pravidel
    -0.77
    rovna
    -0.76
     EVERY
    -0.75
     numai
    -0.73
    armi
    -0.73
     Angebot
    -0.73
    pretation
    -0.73
     mało
    -0.72
    POSITIVE LOGITS
     until
    2.02
     jusqu
    1.66
     até
    1.41
    until
    1.38
     till
    1.37
    Until
    1.28
     hasta
    1.21
     sampai
    1.20
     течение
    1.14
    最後まで
    1.13
    Activations Density 0.058%

    No Known Activations