© 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. 94248
    Prev
    Next
    INDEX
    Explanations

    quantified time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    naments
    -0.82
     mln
    -0.80
     CASO
    -0.79
    一天
    -0.77
     DAYS
    -0.75
     DAY
    -0.75
     Meredith
    -0.75
    ጦ
    -0.75
     quæ
    -0.75
     désormais
    -0.75
    POSITIVE LOGITS
     months
    1.07
    month
    0.99
     month
    0.99
     Monate
    0.85
     měsí
    0.84
     месяцев
    0.84
     bulan
    0.82
    hr
    0.79
     Month
    0.78
     месе
    0.78
    Activations Density 0.041%

    No Known Activations