© 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. 65737
    Prev
    Next
    INDEX
    Explanations

    two categories or types

    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
     numerous
    -1.22
     Numerous
    -1.19
     both
    -1.11
    ceans
    -1.11
    тори
    -1.06
     sowohl
    -1.05
     lẽ
    -1.00
    реди
    -0.98
    lein
    -0.97
    ˜
    -0.96
    POSITIVE LOGITS
     main
    2.70
     types
    2.28
     distinct
    2.08
     kinds
    1.94
     principali
    1.80
    主要
    1.78
     type
    1.77
    main
    1.73
     hlav
    1.73
     principaux
    1.66
    Activations Density 0.146%

    No Known Activations