© 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. 85848
    Prev
    Next
    INDEX
    Explanations

    bowel disease, damage, surgery

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

    references to the bowel or intestinal system in medical contexts.

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

    The neuron detects mentions of the gastrointestinal tract, especially “bowel” and related intestinal terms.

    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
    鸶
    -2.75
    埝
    -2.67
    ᜀ
    -2.48
     rigue
    -2.34
    ーズン
    -2.33
    衚
    -2.30
    U
    -2.23
     gouttes
    -2.19
    又能
    -2.17
    噫
    -2.16
    POSITIVE LOGITS
     When
    2.42
    m
    2.14
     '
    2.09
    FailureListener
    2.09
    ка
    2.08
     With
    2.08
    これが
    2.03
    when
    2.00
    the
    1.98
     if
    1.97
    Activations Density 0.012%

    No Known Activations