© 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. 31-GEMMASCOPE-2-RES-262K
    7. 58411
    Prev
    Next
    INDEX
    Explanations

    equine, horses, and riding

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

    horse riding and equestrianism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    jsonObject
    0.56
    電子
    0.49
     കേസ
    0.45
     都市
    0.45
    不一樣
    0.44
    渦
    0.44
    帙
    0.44
     Chinatown
    0.44
     खाम
    0.43
    ˆ‚
    0.43
    POSITIVE LOGITS
     horses
    1.54
     horse
    1.52
     equine
    1.50
    Horse
    1.38
     Horse
    1.37
     Horses
    1.37
     equestrian
    1.35
    🐴
    1.35
     horseback
    1.34
     dressage
    1.33
    Activations Density 0.113%

    No Known Activations