© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73903
    Prev
    Next
    INDEX
    Explanations

    acronyms and code snippets

    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_10/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
    ↵↵
    -1.77
     innych
    -1.59
     have
    -1.59
    ↵
    -1.55
     حيث
    -1.49
    Debido
    -1.48
    INGREDIENTES
    -1.42
     других
    -1.40
    Existen
    -1.38
     That
    -1.38
    POSITIVE LOGITS
     CGFloat
    1.66
     against
    1.61
     rijk
    1.60
     ());
    1.60
     gouden
    1.56
     CGRectMake
    1.55
    pochette
    1.55
    髕
    1.55
     красивая
    1.52
    一旁
    1.50
    Activations Density 0.063%

    No Known Activations