© 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. 34-GEMMASCOPE-RES-131K
    7. 50451
    Prev
    Next
    INDEX
    Explanations

    programming main function

    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_34/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
     všechny
    -0.99
     всички
    -0.96
     utilização
    -0.93
    ꦿ
    -0.93
     Materialien
    -0.91
     kembali
    -0.90
    ngthen
    -0.90
    fille
    -0.90
     všetky
    -0.89
    koszulka
    -0.89
    POSITIVE LOGITS
     main
    1.13
    ()
    1.11
     ....
    1.05
    If
    1.05
     still
    1.05
    main
    1.01
     one
    0.97
    Just
    0.95
    (
    0.94
     .....
    0.94
    Activations Density 0.009%

    No Known Activations