© 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. 41949
    Prev
    Next
    INDEX
    Explanations

    proteomics and other omics

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

    The neuron detects scientific terms related to proteomics, especially the words "proteome" and "proteomics" and their variants.

    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
    </i>
    -2.94
    艿
    -2.06
    %;
    
    -2.03
    </h5>
    -1.96
    :{
    
    -1.94
    %",
    -1.93
    @",
    -1.89
    "));
    -1.86
    "];
    
    -1.84
    Let
    -1.84
    POSITIVE LOGITS
    </strong>
    2.06
    </h2>
    1.87
     Announces
    1.85
     Launches
    1.78
    Вес
    1.77
    ➲
    1.71
     ruso
    1.71
    .《
    1.70
     "
    1.69
    こども
    1.68
    Activations Density 0.024%

    No Known Activations