© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10046
    Prev
    Next
    INDEX
    Explanations

    influenza and flu outbreaks

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

    The neuron fires on numeric tokens—especially digits and decimal‐number fragments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    堵
    0.54
     Magenta
    0.52
     المل
    0.52
    ზი
    0.52
    ثم
    0.51
     healing
    0.51
    Healing
    0.51
    鍮
    0.50
     тексту
    0.50
    Lightbox
    0.49
    POSITIVE LOGITS
     influenza
    1.52
     Influenza
    1.34
     outbreak
    1.20
     outbreaks
    1.20
     flu
    1.17
     viruses
    1.13
     influenz
    1.00
     Ebola
    0.98
     vírus
    0.98
    viruses
    0.97
    Activations Density 0.174%

    No Known Activations