© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118782
    Prev
    Next
    INDEX
    Explanations

    pathogen infection and host replication

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

    This neuron detects words and phrases related to infectious pathogens, particularly bacteria and parasites, especially in scientific or medical contexts.

    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_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
     ausgeschlossen
    -0.87
     eorum
    -0.84
     ostra
    -0.81
     caballeros
    -0.81
    toISOString
    -0.80
    Config
    -0.78
     правительства
    -0.77
    的他
    -0.77
    haustible
    -0.74
    #
    -0.73
    POSITIVE LOGITS
     host
    1.85
    host
    1.66
     Host
    1.51
    Host
    1.44
    HOST
    1.34
     replication
    1.29
     virulence
    1.19
     entry
    1.06
     HOST
    1.06
     invasion
    1.05
    Activations Density 0.224%

    No Known Activations