© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62940
    Prev
    Next
    INDEX
    Explanations

    free flap reconstructive surgery

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

    medical terminology related to surgical flaps and tissue reconstruction.

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

    The neuron strongly activates on multi‐word anatomical and surgical procedure terms, especially names of reconstructive “flaps.”

    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
     초
    -0.82
    僱
    -0.78
     Pacheco
    -0.78
     kemasan
    -0.74
    achy
    -0.72
    Retirement
    -0.72
     setText
    -0.72
    ceu
    -0.70
     barato
    -0.69
     sabía
    -0.69
    POSITIVE LOGITS
     flap
    1.74
     flaps
    1.64
    flap
    1.28
     Flap
    1.18
     skin
    1.03
    recipient
    1.03
     Hunde
    0.98
    Recipient
    0.96
    Skin
    0.93
    Island
    0.92
    Activations Density 0.203%

    No Known Activations