© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9764
    Prev
    Next
    INDEX
    Explanations

    cowboys and the old west

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

    western cowboy frontier themes

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

    cowboys

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChartView
    0.43
     Bhatt
    0.42
    न्नाथ
    0.42
    柊
    0.42
     Jiangsu
    0.41
     phường
    0.40
     Goddess
    0.40
    静岡
    0.40
     ভট্টাচার্য
    0.40
     Arnav
    0.39
    POSITIVE LOGITS
     cowboys
    1.80
     cowboy
    1.77
     Cowboy
    1.58
     Cowboys
    1.53
    🤠
    1.47
     rodeo
    1.41
    牛仔
    1.27
     ranchers
    1.26
     Rodeo
    1.23
     ranch
    1.19
    Activations Density 0.374%

    No Known Activations