© 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. 30199
    Prev
    Next
    INDEX
    Explanations

    former officials and past times

    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
     lately
    -1.68
     recently
    -1.68
     Recently
    -1.57
     currently
    -1.41
     new
    -1.35
    Recently
    -1.34
     newest
    -1.33
    recent
    -1.32
    最近
    -1.29
     yesterday
    -1.27
    POSITIVE LOGITS
     then
    4.69
     тогда
    3.55
     entonces
    3.19
     damaligen
    3.09
     damals
    2.98
    當時
    2.94
     então
    2.77
    Then
    2.77
     wtedy
    2.77
     allora
    2.75
    Activations Density 0.086%

    No Known Activations