© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75393
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    ños
    -1.53
     onun
    -1.38
     is
    -1.33
     eral
    -1.32
    ਗ਼
    -1.31
    tifiable
    -1.31
    www
    -1.30
    
    -1.28
     jego
    -1.28
     его
    -1.28
    POSITIVE LOGITS
     and
    1.90
     then
    1.71
     which
    1.70
     all
    1.55
     each
    1.48
     あります
    1.48
     these
    1.45
     where
    1.45
     so
    1.32
    Aceite
    1.32
    Activations Density 0.084%

    No Known Activations