© 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. 39981
    Prev
    Next
    INDEX
    Explanations

    horse racing and breeding

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

    thoroughbred horses and racing

    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
     સમગ્ર
    0.56
    🥨
    0.55
    ☦
    0.55
    选举
    0.54
    蚩
    0.54
     მთავ
    0.54
     سیاسی
    0.53
    冲突
    0.53
    䏹
    0.53
     वस्तू
    0.53
    POSITIVE LOGITS
     caballos
    0.85
     horses
    0.79
     breeders
    0.79
     filly
    0.79
     yearling
    0.76
     heifers
    0.72
     paddock
    0.71
     Thoroughbred
    0.71
     femelles
    0.68
     progeny
    0.68
    Activations Density 0.033%

    No Known Activations