© 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. 65750
    Prev
    Next
    INDEX
    Explanations

    vaccines and vaccination

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

    words related to vaccines and vaccination in medical and scientific contexts.

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

    The main thing this neuron does is detect mentions of vaccines, vaccination, or immunization.

    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
    唏
    -0.86
     स्थित
    -0.85
    普通の
    -0.84
     cull
    -0.80
    ot
    -0.80
    ou
    -0.80
          
    -0.80
    ⵎ
    -0.80
     frische
    -0.80
    om
    -0.80
    POSITIVE LOGITS
    ių
    1.04
     rollout
    0.98
    💉
    0.96
     preventable
    0.93
     dispuestos
    0.93
     refuser
    0.91
     provider
    0.91
     препара
    0.90
     against
    0.89
    FTAR
    0.88
    Activations Density 0.019%

    No Known Activations