© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 64821
    Prev
    Next
    INDEX
    Explanations

    course of, Rodney Crowell

    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
     сахара
    -1.11
     because
    -1.09
    bilen
    -1.03
    kwal
    -0.97
     really
    -0.96
     \\
    
    -0.96
    扁平
    -0.95
    {}/
    -0.94
    婚礼
    -0.92
    ׇ
    -0.92
    POSITIVE LOGITS
     verschillende
    1.13
     موبایل
    1.12
    וּ
    1.11
    ּוֹ
    1.09
    ַּ
    1.08
     различных
    1.07
     deportivas
    1.05
    ͆
    1.04
    色んな
    1.02
    轻松
    1.02
    Activations Density 0.001%

    No Known Activations