© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124583
    Prev
    Next
    INDEX
    Explanations

    ulcerative or ulceration

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

    The neuron detects medical terms related to ulcerative colitis and other inflammatory conditions.

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

    This neuron strongly activates on mentions of the disease “ulcerative colitis” (or its component “ulcerative”).

    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
     แต่
    -2.66
    耜
    -2.50
    大きさ
    -2.50
    ⁧
    -2.48
     momentous
    -2.48
     horrifying
    -2.45
     dreadful
    -2.44
    糨
    -2.41
     But
    -2.38
    尴
    -2.36
    POSITIVE LOGITS
    0
    2.77
    can
    2.53
    6
    2.28
    ↵↵
    2.23
    All
    2.20
    _{
    2.17
    第二
    2.17
    ↵
    2.17
    …..
    2.17
    From
    2.16
    Activations Density 0.009%

    No Known Activations