© 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. 32573
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    <bos>
    -1.06
     other
    -1.05
     conclusions
    -0.94
    がある
    -0.94
     conclusion
    -0.94
    墜
    -0.94
     cuando
    -0.93
     which
    -0.92
    analyser
    -0.90
     times
    -0.87
    POSITIVE LOGITS
    Río
    0.97
    Доку
    0.93
    UNCH
    0.88
    ⎨
    0.88
    ̃o
    0.86
    rtner
    0.85
    blé
    0.84
    LLAB
    0.84
    時々
    0.84
    ਝ
    0.84
    Activations Density 0.011%

    No Known Activations