© 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. 10-GEMMASCOPE-RES-131K
    7. 7610
    Prev
    Next
    INDEX
    Explanations

    spinal deformity surgery

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

    technical or medical terms describing physical deformities or abnormalities.

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

    This neuron responds to uncommon technical or domain‐specific terms (e.g. “deformity,” “scoliosis,” “binom”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     That
    -4.22
     Also
    -2.81
     что
    -2.72
    section
    -2.61
     Get
    -2.58
     allgemeinen
    -2.58
     Does
    -2.52
     dejando
    -2.47
     egregious
    -2.44
     italienischen
    -2.41
    POSITIVE LOGITS
    箆
    2.70
    踅
    2.69
    ≐
    2.63
    蹀
    2.61
    It
    2.59
    ꯲
    2.59
     ™
    2.55
     بدر
    2.55
     髪型
    2.47
     唯美
    2.42
    Activations Density 0.003%

    No Known Activations