© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10383
    Prev
    Next
    INDEX
    Explanations

    horse, equine, equestrian activities

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

    horse, equine, equestrian

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

    horse

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    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
     kivy
    0.46
    expat
    0.42
    weiler
    0.39
    шком
    0.38
    DBGPRINT
    0.38
    ャ
    0.38
    នុ
    0.38
     रामानंद
    0.37
     буль
    0.37
    蝌
    0.37
    POSITIVE LOGITS
     horses
    2.08
     horse
    2.06
     Horses
    1.93
    Horse
    1.91
     Horse
    1.91
     equine
    1.84
     caballos
    1.76
     Pferde
    1.76
    🐴
    1.76
    horse
    1.73
    Activations Density 0.306%

    No Known Activations