© 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. 22-GEMMASCOPE-RES-131K
    7. 67150
    Prev
    Next
    INDEX
    Explanations

    body parts and locations

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

    parts of the body or anatomical locations in medical texts.

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

    The neuron fires on anatomical or bodily-location terms (body parts, organs, sites).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    kanı
    -1.16
    ModelAttribute
    -1.14
     nuits
    -1.13
     encephalitis
    -1.06
     rôles
    -1.06
     epilepsy
    -1.05
     ſon
    -1.04
     to
    -1.04
    消失了
    -1.04
     nhat
    -1.03
    POSITIVE LOGITS
     areas
    1.70
     regions
    1.34
    specific
    1.27
     शरीर
    1.24
     locations
    1.23
     regiões
    1.23
    Gdzie
    1.16
    ड़
    1.16
    čenie
    1.16
     sites
    1.15
    Activations Density 0.167%

    No Known Activations