© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12132
    Prev
    Next
    INDEX
    Explanations

    equine limb anatomy and pathology

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

    anatomical terms related to animal limbs and hooves, particularly in horses and other quadrupeds.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     abdominal
    -0.96
     neck
    -0.92
     lumbar
    -0.82
     Abdominal
    -0.81
    mål
    -0.76
     nose
    -0.76
     stomach
    -0.75
     waist
    -0.75
     asthma
    -0.75
    ンドル
    -0.75
    POSITIVE LOGITS
     hoof
    1.37
    蹄
    1.15
     digital
    0.93
     hooves
    0.91
     Hoof
    0.91
     digitale
    0.90
    rollment
    0.87
    hoof
    0.86
    Digit
    0.85
     pedicure
    0.84
    Activations Density 0.017%

    No Known Activations