© 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. 106472
    Prev
    Next
    INDEX
    Explanations

    sales and date ranges

    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
    Not in Any Lists

    No Comments

    Negative Logits
     öf
    -0.84
     if
    -0.83
    ู่
    -0.83
    佛
    -0.82
    cheque
    -0.82
     cristianos
    -0.82
     chré
    -0.80
     čier
    -0.80
    规格
    -0.80
    そろ
    -0.80
    POSITIVE LOGITS
     month
    2.20
     today
    1.97
     yesterday
    1.78
     summary
    1.73
     year
    1.70
     week
    1.67
     total
    1.64
     monthly
    1.63
     last
    1.52
     Month
    1.48
    Activations Density 0.063%

    No Known Activations