Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8622
    Prev
    Next
    INDEX
    Explanations

    inflammatory bowel disease

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

    The neuron detects phrases related to inflammatory diseases, particularly "inflammatory bowel disease" and related medical conditions.

    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_34/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
     描述
    -1.04
    According
    -0.98
     Kristus
    -0.92
    Luckily
    -0.90
    Currently
    -0.90
    Nevertheless
    -0.88
    Furthermore
    -0.87
     valore
    -0.86
     abject
    -0.86
    Whether
    -0.85
    POSITIVE LOGITS
     response
    1.22
    response
    1.09
     and
    1.05
     responses
    1.02
     Response
    1.01
     bowel
    0.96
     reaction
    0.94
     RESPONSE
    0.94
    reaction
    0.90
     responded
    0.88
    Activations Density 0.028%

    No Known Activations