© 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. 22-GEMMASCOPE-RES-131K
    7. 28395
    Prev
    Next
    INDEX
    Explanations

    numbers immediately following symbols

    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_22/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
    Тарихы
    -0.95
    hij
    -0.90
     blik
    -0.88
    писки
    -0.87
    ensively
    -0.85
    вік
    -0.85
    ρων
    -0.84
    lahraga
    -0.84
    tagez
    -0.84
     menac
    -0.82
    POSITIVE LOGITS
     unleash
    1.07
     immediately
    0.92
     empty
    0.85
     diminutive
    0.83
     stepping
    0.82
     helping
    0.78
    ['
    0.78
     confezione
    0.76
     --
    0.75
    贅沢
    0.75
    Activations Density 0.001%

    No Known Activations