© 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. 98666
    Prev
    Next
    INDEX
    Explanations

    times with p.m

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

    The neuron activates on numeric expressions—digits, years, dates, times, and related number‐like tokens.

    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
     for
    -1.60
    姈
    -1.41
     magasiner
    -1.41
     ۲۰۰
    -1.35
    jectable
    -1.35
     potřeb
    -1.33
     ۱۳۸
    -1.32
     setObject
    -1.30
     sommar
    -1.30
     setTotal
    -1.30
    POSITIVE LOGITS
     из
    1.43
     two
    1.36
     three
    1.27
     similar
    1.25
    endwhile
    1.25
     four
    1.25
     fellow
    1.25
     treino
    1.25
     last
    1.24
     have
    1.22
    Activations Density 0.082%

    No Known Activations