© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2650
    Prev
    Next
    INDEX
    Explanations

    COVID pandemic

    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_16_width_65k_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
    ش
    1.00
     as
    0.89
    ف
    0.89
     were
    0.88
    ك
    0.84
    ب
    0.82
    क
    0.81
    ق
    0.81
    ক
    0.79
    ,
    0.79
    POSITIVE LOGITS
    AN
    0.82
    IN
    0.79
    -
    0.71
    ON
    0.69
    pandemic
    0.66
    োম
    0.65
    WRITE
    0.64
    ALK
    0.64
    AL
    0.63
    CH
    0.63
    Activations Density 0.003%

    No Known Activations