© 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. 22-GEMMASCOPE-RES-131K
    7. 25177
    Prev
    Next
    INDEX
    Explanations

    paralympics and summer events

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    なもの
    -1.16
    なこと
    -1.00
     miljoner
    -0.97
    헷
    -0.97
     جورج
    -0.93
    粜
    -0.93
     sekret
    -0.92
    menin
    -0.92
     Danh
    -0.92
     miniaturka
    -0.91
    POSITIVE LOGITS
     what
    1.24
     if
    1.05
    Bags
    0.95
    編曲
    0.95
     many
    0.95
     possibly
    0.90
     tersangka
    0.89
     simple
    0.84
    Monty
    0.84
     even
    0.83
    Activations Density 0.031%

    No Known Activations