© 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. 34-GEMMASCOPE-RES-131K
    7. 63380
    Prev
    Next
    INDEX
    Explanations

    rodeo and cowboy career

    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_34/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
    デバイス
    -0.81
     grayscale
    -0.80
     follic
    -0.75
    மை
    -0.74
     effectivement
    -0.73
     مدیر
    -0.73
    whal
    -0.71
    kanı
    -0.71
     muối
    -0.70
    CONV
    -0.70
    POSITIVE LOGITS
     rodeo
    1.12
     cattle
    1.09
     cowboy
    1.03
     livestock
    1.00
     arena
    0.97
     WORLD
    0.91
     Cowboy
    0.91
     cow
    0.87
     earnings
    0.85
     Cattle
    0.84
    Activations Density 0.012%

    No Known Activations