© 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. 9704
    Prev
    Next
    INDEX
    Explanations

    Standard art reference

    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
    了些
    -1.72
     zoals
    -1.57
     zrobić
    -1.55
    了不少
    -1.45
     Coruña
    -1.43
    fielder
    -1.40
    urgery
    -1.36
     Ediciones
    -1.35
     попробовать
    -1.34
    byes
    -1.34
    POSITIVE LOGITS
     that
    2.23
     there
    1.95
     very
    1.70
     every
    1.59
     other
    1.57
     time
    1.57
     have
    1.57
     three
    1.55
     mencionar
    1.52
     until
    1.42
    Activations Density 0.137%

    No Known Activations