© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12015
    Prev
    Next
    INDEX
    Explanations

    Coronavirus and lockdown terms

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

    coronavirus pandemic and societal impacts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    🥹
    0.77
     ২০২৩
    0.75
    🥲
    0.73
     २०२
    0.72
     ২০২২
    0.69
    🫢
    0.69
    🫶
    0.66
    🫠
    0.66
     unvaccinated
    0.66
    🫣
    0.66
    POSITIVE LOGITS
     Coronavirus
    0.62
     coronavirus
    0.61
    coronavirus
    0.57
    Coronavirus
    0.55
     করোনাভাই
    0.55
     APRIL
    0.51
     लॉकडाउन
    0.50
    april
    0.48
    लॉक
    0.47
     April
    0.47
    Activations Density 0.011%

    No Known Activations