© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116370
    Prev
    Next
    INDEX
    Explanations

    spinal deformities and correction

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

    The neuron identifies medical terminology related to spinal conditions, deformities, and orthopedic disorders, particularly focusing on terms like "scoliosis," "kyphosis," "valgus," and other skeletal misalignments.

    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
    生肖
    -0.90
     Croydon
    -0.78
    🇪
    -0.77
    ABEL
    -0.76
    OpenGL
    -0.74
     concussion
    -0.72
    ➜
    -0.72
    Abu
    -0.72
     waxing
    -0.71
    Kund
    -0.71
    POSITIVE LOGITS
     correction
    1.41
     deformity
    1.38
    correction
    1.25
     sco
    1.20
     deform
    1.20
     corrective
    1.09
     curves
    1.08
     curvature
    1.05
     Correction
    1.04
    sco
    0.98
    Activations Density 0.154%

    No Known Activations