© 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. 9104
    Prev
    Next
    INDEX
    Explanations

    messi

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

    The neuron strongly activates on mentions of specific pathogens or toxins (e.g., virus or toxin names).

    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
    Citizens
    0.75
    💰
    0.72
     নানান
    0.72
    financ
    0.71
    camiseta
    0.70
    土地
    0.69
    govt
    0.69
    Business
    0.69
     невероят
    0.69
    ってる
    0.68
    POSITIVE LOGITS
     melanogaster
    0.82
     $(\
    0.81
     $^{
    0.81
     axisymmetric
    0.79
     type
    0.78
     uniaxial
    0.77
     $(
    0.75
     studied
    0.74
     AcOEt
    0.74
     $_{\
    0.74
    Activations Density 0.232%

    No Known Activations