© 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. 916
    Prev
    Next
    INDEX
    Explanations

    took time or effort

    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
     anything
    -1.62
     something
    -1.50
     usually
    -1.48
    [
    -1.46
    &
    -1.45
    =
    -1.43
     any
    -1.41
     want
    -1.39
     [
    -1.39
    !
    -1.38
    POSITIVE LOGITS
     rése
    1.55
    kese
    1.52
     mikrofon
    1.49
     parfü
    1.48
     vermel
    1.48
     dekol
    1.45
     gondol
    1.45
     éton
    1.43
     transak
    1.41
     bluz
    1.41
    Activations Density 0.022%

    No Known Activations