© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19166
    Prev
    Next
    INDEX
    Explanations

    special characters followed by words

    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
    s
    -2.91
     часу
    -2.17
    のも
    -2.17
    ers
    -2.16
     версия
    -2.11
    瑧
    -2.02
     “
    -1.94
     福袋
    -1.91
     проблеми
    -1.91
    m
    -1.91
    POSITIVE LOGITS
     ........
    2.72
     .........
    2.63
     "
    2.30
     "(
    2.22
     '[
    2.20
     .......
    2.20
    翃
    2.19
    ...."
    2.19
     illustrate
    2.17
     "&
    2.17
    Activations Density 0.049%

    No Known Activations