© 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. 9069
    Prev
    Next
    INDEX
    Explanations

    common abbreviations and prefixes

    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
     несмотря
    -1.77
     Without
    -1.72
     provides
    -1.61
     without
    -1.60
     Because
    -1.58
     They
    -1.57
     With
    -1.55
     поэтому
    -1.50
     Generally
    -1.49
     Для
    -1.48
    POSITIVE LOGITS
     etek
    1.70
     boya
    1.63
     diki
    1.60
     comportements
    1.55
     gogh
    1.55
     eléct
    1.51
     groen
    1.48
     inim
    1.48
     énorme
    1.45
     biet
    1.45
    Activations Density 0.052%

    No Known Activations