© 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. 99655
    Prev
    Next
    INDEX
    Explanations

    ileal, ileostomy, ileum, ileocecal

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

    The neuron identifies medical terms related to the ileum (small intestine).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    臯
    -3.09
    鲼
    -2.72
    솝
    -2.70
    i
    -2.63
    揠
    -2.48
    拚
    -2.48
     pharmacie
    -2.45
    𓋼
    -2.44
    萏
    -2.42
    鈁
    -2.41
    POSITIVE LOGITS
    "
    3.36
    ).
    2.80
     Then
    2.52
    当然
    2.48
    は
    2.47
    _
    2.45
     With
    2.23
     altre
    2.22
     Notably
    2.22
    </sup>
    2.20
    Activations Density 0.001%

    No Known Activations