© 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. 72346
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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_10/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
     \
    -1.88
     alguns
    -1.58
     muitos
    -1.55
     a
    -1.51
     três
    -1.50
     are
    -1.48
     ‘‘
    -1.48
     DIFFERENT
    -1.46
     
    -1.45
     of
    -1.45
    POSITIVE LOGITS
     Deletes
    1.58
     äußerst
    1.54
     Numerous
    1.53
     from
    1.50
     Relatively
    1.48
    orexia
    1.46
     âmes
    1.45
    alamualaikum
    1.45
     PUSTAKA
    1.44
     Füßen
    1.44
    Activations Density 0.002%

    No Known Activations