© 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. 117963
    Prev
    Next
    INDEX
    Explanations

    biological cultures

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

    medical laboratory procedures and terminology related to cultures, specimens, and diagnostic testing.

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

    The neuron strongly activates on terminology describing laboratory diagnostic methods and procedures (e.g. culture, microscopy, histopathology, retrospective review) in a clinical microbiology context.

    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
    Corr
    -0.76
    חס
    -0.74
    punten
    -0.73
    dchen
    -0.71
    essi
    -0.71
     haberse
    -0.71
    ตุ
    -0.70
     Fest
    -0.69
    เป๋า
    -0.69
    חים
    -0.68
    POSITIVE LOGITS
     culture
    2.41
     cultures
    2.25
    culture
    1.98
     Culture
    1.87
     Cultures
    1.75
    Culture
    1.73
     cultivation
    1.70
     CULTURE
    1.65
     cultured
    1.65
    文化
    1.65
    Activations Density 0.146%

    No Known Activations