© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8655
    Prev
    Next
    INDEX
    Explanations

    pandemic COVID-19 and coronavirus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    мент
    0.77
     сообщение
    0.74
    ರ್ಧ
    0.73
     mensagem
    0.71
     arquivo
    0.70
    żą
    0.70
    ときに
    0.70
    た
    0.69
    𝚣
    0.68
    лее
    0.68
    POSITIVE LOGITS
     Coronavirus
    1.70
    Coronavirus
    1.64
     COVID
    1.61
    COVID
    1.59
    Covid
    1.58
     Covid
    1.57
    疫情
    1.54
     pandemic
    1.53
    covid
    1.51
     coronavirus
    1.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.