© 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. 38549
    Prev
    Next
    INDEX
    Explanations

    future year

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

    The neuron fires on numeric tokens—especially digits, measurements, section or figure numbers, and other numeral expressions.

    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
    :
    -1.33
     endwhile
    -1.09
     vinaigre
    -1.07
     venezolano
    -1.06
    􀂃
    -1.06
     volonté
    -1.06
    に向かって
    -1.06
    着一个
    -1.06
     erbjud
    -1.05
    ǰ
    -1.05
    POSITIVE LOGITS
     både
    1.36
     its
    1.34
     разных
    1.28
     suoi
    1.23
    tanleria
    1.20
     различных
    1.17
    今日
    1.16
     bulan
    1.16
     также
    1.14
     також
    1.14
    Activations Density 0.746%

    No Known Activations