© 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. 679
    Prev
    Next
    INDEX
    Explanations

    meningococcal meningitis

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

    This neuron detects scientific terminology related to bacteria and pathogens, particularly species names like "Neisseria gonorrhoeae" and "Pneumococcal".

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

    The neuron responds strongly to mentions of bacterial disease names ending in “-coccal” (e.g. meningococcal, pneumococcal).

    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
    ップ
    -0.71
    jungan
    -0.69
    UCE
    -0.68
     resaltar
    -0.68
    =()
    -0.68
     Vice
    -0.68
    鬨
    -0.68
     arreg
    -0.65
    kq
    -0.65
     treat
    -0.65
    POSITIVE LOGITS
     Mening
    1.53
     meningitis
    1.39
     mening
    1.28
    mening
    1.18
    Mening
    1.12
     pili
    0.92
     Conjug
    0.89
    conjug
    0.87
     Bex
    0.87
     valent
    0.85
    Activations Density 0.051%

    No Known Activations