© 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. 16551
    Prev
    Next
    INDEX
    Explanations

    symbols, mathematical operators

    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
     innumerable
    -3.17
     plethora
    -3.16
     शुर
    -3.11
     unrelenting
    -3.09
     impeccable
    -3.00
     Ironically
    -2.98
     Usually
    -2.97
     superbly
    -2.92
     Using
    -2.89
     Almost
    -2.89
    POSITIVE LOGITS
    蹰
    3.22
    to
    3.06
    秾
    2.97
     Dinas
    2.88
     magnific
    2.88
     terrific
    2.86
     delightfully
    2.81
     reiter
    2.78
    냑
    2.75
    女孩子
    2.72
    Activations Density 0.024%

    No Known Activations