© 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. 25922
    Prev
    Next
    INDEX
    Explanations

    osteopathic manipulative treatment

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

    terms related to osteopathic medicine, particularly those containing 'ili' and 'ac' like in 'iliac' when discussing medical conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on specialized medical terminology—especially osteopathic/manual‐medicine jargon like “sacroiliac,” “dysfunction,” “osteopathic,” and “manipulative.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    事例
    -0.83
    TabStop
    -0.75
     glances
    -0.75
     selfies
    -0.74
     cama
    -0.73
     Wund
    -0.72
     磁
    -0.72
     Shower
    -0.71
     Salve
    -0.71
     configurable
    -0.70
    POSITIVE LOGITS
     manipulation
    1.30
    manip
    1.27
     Manip
    1.16
     manipulative
    1.14
     Manipulation
    1.13
    Manip
    1.13
     manipulations
    1.13
     manip
    1.09
     manual
    1.06
     techniques
    1.06
    Activations Density 0.018%

    No Known Activations