© 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. 10-GEMMASCOPE-RES-131K
    7. 43082
    Prev
    Next
    INDEX
    Explanations

    parathyroid gland and hormone

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

    medical terms related to the parathyroid gland and parathyroid hormone.

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

    The neuron specifically detects mentions of (primary) hyperparathyroidism (i.e. the multi­token phrase “hyper-parathyroid-ism” or its abbreviations).

    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
    ocrats
    -1.41
     [...]
    -1.34
    [...]
    -1.28
     gefe
    -1.28
    вні
    -1.17
    螣
    -1.14
    汌
    -1.14
    "=>"
    -1.14
     書
    -1.13
    。　　
    -1.12
    POSITIVE LOGITS
     sym
    1.50
    揷
    1.38
    噚
    1.36
     tid
    1.35
    澇
    1.32
    ernalia
    1.30
    tadır
    1.28
     การ์ตูน
    1.27
     กล่อง
    1.26
     Reised
    1.23
    Activations Density 0.197%

    No Known Activations