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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14727
    Prev
    Next
    INDEX
    Explanations

    influenza virus vaccination

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

    The neuron activates on mentions of "influenza" virus, showing highest activation for this specific disease term.

    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_10/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
    '
    -2.72
    0
    -2.61
    1
    -2.48
    也将
    -2.25
     gelassen
    -2.22
    乆
    -2.22
    しながら
    -2.19
    système
    -2.16
     fuimos
    -2.09
    ांकि
    -2.02
    POSITIVE LOGITS
    ↵↵
    3.92
    剮
    3.09
    щита
    2.80
    餮
    2.80
    “
    2.73
    窳
    2.64
     mayoría
    2.58
    柺
    2.53
    咙
    2.42
     You
    2.33
    Activations Density 0.007%

    No Known Activations