© 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. 32975
    Prev
    Next
    INDEX
    Explanations

    date comparison operators

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

    The neuron responds to date/time or timestamp expressions—especially comparisons and literal date values—in SQL queries.

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

    No Comments

    Negative Logits
     блюдо
    -1.13
    就有
    -0.96
    Torna
    -0.94
    <bos>
    -0.89
     kawaida
    -0.86
    ()==
    -0.86
     sempre
    -0.85
    บน
    -0.85
    有时候
    -0.84
     thả
    -0.84
    POSITIVE LOGITS
     pensent
    1.16
    хие
    1.09
     Preferencias
    1.07
     time
    1.02
     hábiles
    0.93
    {§
    0.92
    ije
    0.91
     Ива
    0.90
    极了
    0.90
     Início
    0.89
    Activations Density 0.014%

    No Known Activations