© 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. 34-GEMMASCOPE-RES-131K
    7. 56713
    Prev
    Next
    INDEX
    Explanations

    time, timestamps, or synchronization

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

    The neuron is primarily sensitive to numeric and measurement‐style tokens (e.g. raw numbers, time values, sample/window sizes, timestamps).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     inteligencia
    -0.81
     Opin
    -0.73
     interact
    -0.72
    //////////////
    -0.71
     unfinished
    -0.71
     reak
    -0.70
    原始内容存档于
    -0.69
     spek
    -0.69
    Instant
    -0.68
    mogen
    -0.68
    POSITIVE LOGITS
     SMP
    1.08
    code
    0.97
     LTC
    0.93
    SMP
    0.84
    VIT
    0.84
    计数
    0.81
     smp
    0.81
    ί
    0.81
    代码
    0.79
     ticks
    0.77
    Activations Density 0.040%

    No Known Activations