© 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. 130740
    Prev
    Next
    INDEX
    Explanations

    medical conditions and procedures

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

    The neuron activates for words related to gastrointestinal illness, particularly "diarrhea" and "plagiarized/plagiarism".

    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
    𖤍
    -3.48
    釹
    -3.11
    櫚
    -3.05
    𖤣
    -3.00
    ৢ
    -2.89
    籥
    -2.88
    傚
    -2.83
    ⸂
    -2.80
    ⾔
    -2.77
    cuterie
    -2.75
    POSITIVE LOGITS
     
    3.73
    .
    3.08
    ↵
    2.89
    0
    2.88
    {
    2.72
    g
    2.52
    ’
    2.48
    on
    2.39
    3
    2.17
    さっき
    2.14
    Activations Density 0.011%

    No Known Activations