© 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. 34-GEMMASCOPE-RES-131K
    7. 81173
    Prev
    Next
    INDEX
    Explanations

    Escherichia coli

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

    scientific terminology in microbiology and bacteria research papers.

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

    The neuron activates on technical phrases naming fecal indicator bacteria (e.g. enterococci as FIB) in water‐quality or environmental microbiology contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    گوشی
    -0.83
     MaterialApp
    -0.76
    pod
    -0.73
     BeautifulSoup
    -0.73
     docked
    -0.73
     heureux
    -0.70
    pObj
    -0.70
     triunfo
    -0.70
     dipa
    -0.69
    mas
    -0.68
    POSITIVE LOGITS
    MPN
    1.24
     coli
    1.23
     fecal
    1.06
     MP
    1.05
     indicator
    0.99
     Coli
    0.95
    coli
    0.87
     indicators
    0.87
     Indicators
    0.84
    indicators
    0.82
    Activations Density 0.028%

    No Known Activations