© 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. 53842
    Prev
    Next
    INDEX
    Explanations

    infection contexts

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

    discussions of infectious agents, pathogens, or disease-causing microorganisms in scientific or medical contexts.

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

    The neuron fires on technical microbiology terms describing pathogen detection, identification, infection, survival, or replication processes.

    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
     Stanisław
    -0.75
     Zeugen
    -0.74
    transfer
    -0.73
    μισ
    -0.73
     każde
    -0.72
    éléments
    -0.71
    cuss
    -0.71
    guan
    -0.70
     løs
    -0.70
    acas
    -0.70
    POSITIVE LOGITS
     infection
    5.81
     infections
    4.91
     Infection
    4.53
    infection
    4.22
    Infection
    4.06
     Infections
    3.67
    感染
    3.52
     infected
    3.19
     инфек
    2.83
     infección
    2.73
    Activations Density 0.332%

    No Known Activations