© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5164
    Prev
    Next
    INDEX
    Explanations

    COVID pandemic and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ২০১৫
    0.53
     Skype
    0.52
    🐀
    0.48
    铳
    0.44
    ⁢</
    0.43
     aik
    0.42
     JY
    0.42
    萤
    0.41
    Lip
    0.41
     islet
    0.41
    POSITIVE LOGITS
     ২০২১
    1.14
     Covid
    1.08
     covid
    1.02
     vaccination
    1.01
    Covid
    1.00
     pandemia
    0.97
     COVID
    0.95
     vaccine
    0.94
    covid
    0.93
    COVID
    0.92
    Activations Density 0.240%

    No Known Activations