© 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. 251
    Prev
    Next
    INDEX
    Explanations

    package names and programming constructs

    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
    гули
    -1.17
    ⟷
    -1.13
    iforms
    -1.13
     sikre
    -1.13
    хла
    -1.06
    +',
    -1.01
     gøre
    -1.01
     tilby
    -0.99
     centímetros
    -0.97
     bruge
    -0.95
    POSITIVE LOGITS
     mélanger
    1.23
    They
    1.08
    Consequently
    0.99
    さっき
    0.99
    SwingConstants
    0.98
    Known
    0.94
     They
    0.94
    ronesia
    0.93
    Fortunately
    0.93
    分鐘
    0.93
    Activations Density 0.004%

    No Known Activations