© 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. 113012
    Prev
    Next
    INDEX
    Explanations

    Objective-C/Swift declarations

    np_acts-logits-general · gemini-2.5-flash-lite

    property declarations in Objective-C code, particularly after the closing parenthesis of property attributes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     to
    -1.98
    then
    -1.61
     سپس
    -1.54
     zukünf
    -1.50
     двумя
    -1.49
     dabar
    -1.48
     bestimmten
    -1.48
    当時の
    -1.47
    开玩笑
    -1.47
     gewährle
    -1.46
    POSITIVE LOGITS
    ísticos
    1.73
    λία
    1.62
    Médaille
    1.61
    ertia
    1.48
    　　“
    1.45
    \|^{
    1.43
    angkutan
    1.43
    也
    1.41
    ！！！”
    1.41
    PAUL
    1.41
    Activations Density 0.003%

    No Known Activations