© 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. 119091
    Prev
    Next
    INDEX
    Explanations

    display orientation

    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
    jsoup
    -1.03
    nosed
    -0.96
     नाम
    -0.94
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.89
    atud
    -0.88
     哪些
    -0.88
    짙
    -0.88
    被告
    -0.88
     市場
    -0.85
    wired
    -0.85
    POSITIVE LOGITS
    children
    1.13
     children
    1.05
     main
    1.05
     hoved
    0.97
     (
    0.97
    Children
    0.94
     cross
    0.94
     Children
    0.94
     transak
    0.92
    main
    0.90
    Activations Density 0.001%

    No Known Activations