© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116000
    Prev
    Next
    INDEX
    Explanations

    knee joint instability and repair

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

    This neuron activates for anatomical terms related to knee and joint structures, particularly focusing on medical terminology like ligaments, joints, and bone structures.

    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
     shoulder
    -1.23
    shoulder
    -1.16
     wrist
    -1.02
     Shoulder
    -1.02
     shoulders
    -1.02
     neck
    -0.98
    Shoulder
    -0.88
    颈
    -0.87
     wrists
    -0.84
    neck
    -0.83
    POSITIVE LOGITS
     knee
    1.80
     Knee
    1.63
    Knee
    1.59
     kne
    1.54
     knees
    1.38
    knee
    1.36
     Kne
    1.34
     kneeling
    1.33
    膝
    1.27
     kneel
    1.23
    Activations Density 0.101%

    No Known Activations