© 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. 10-GEMMASCOPE-RES-131K
    7. 130997
    Prev
    Next
    INDEX
    Explanations

    anatomy and anatomical competence

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

    the word "anatomy" and related anatomical terms in medical or scientific contexts.

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

    The neuron activates on occurrences of the term “anatomy” (and its close variants like anatomic/anatomical).

    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
    鹮
    -2.34
    喏
    -2.30
    人也
    -2.27
    齜
    -2.17
     Of
    -2.11
     are
    -2.02
    üdis
    -1.94
    zás
    -1.88
    ⽤
    -1.86
    ][$
    -1.85
    POSITIVE LOGITS
    ↵
    3.41
    D
    2.88
    E
    2.80
    ”
    2.53
    ”،
    2.48
    ”]
    2.44
    </h2>
    2.39
    O
    2.33
    .”)
    2.25
    ”)
    2.22
    Activations Density 0.012%

    No Known Activations