© 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. 34-GEMMASCOPE-RES-131K
    4. 66158
    Prev
    Next
    INDEX
    Explanations

    immune responses and tolerance

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

    academic language related to immunology research, particularly focusing on T cells and immune responses.

    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
     chré
    -1.23
     erbjuder
    -1.17
     caballeros
    -1.08
    ὴν
    -1.02
     baskılı
    -1.01
     kumaş
    -1.00
    FPGA
    -0.98
     Nedir
    -0.95
     carteles
    -0.95
     pageNo
    -0.95
    POSITIVE LOGITS
     Immunol
    1.44
     helper
    0.99
     Immunology
    0.98
     CD
    0.97
    immune
    0.96
     responder
    0.96
    stander
    0.96
     boost
    0.94
     toler
    0.93
    danger
    0.93
    Activations Density 0.428%

    No Known Activations