© 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. 11260
    Prev
    Next
    INDEX
    Explanations

    Crohn's disease

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

    mentions of Crohn's disease in medical or scientific contexts.

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

    The neuron predominantly fires on occurrences of “Crohn” (i.e. mentions of Crohn’s disease).

    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
    踅
    -2.75
    ㉨
    -2.55
    緜
    -2.50
     It
    -2.39
    亊
    -2.38
     decidi
    -2.31
    al
    -2.30
    亍
    -2.28
    怱
    -2.27
    廡
    -2.25
    POSITIVE LOGITS
    {
    2.67
    ată
    2.56
    ↵
    2.52
    桝
    2.33
     проекта
    2.23
    但不
    2.16
     bekannte
    2.08
     '\\
    2.08
    ?
    2.08
    .”
    2.06
    Activations Density 0.011%

    No Known Activations