© 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-262K
    7. 67299
    Prev
    Next
    INDEX
    Explanations

    diseases

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

    COVID-19

    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_262k_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
     Vuk
    0.55
    اج
    0.54
    ς
    0.53
    ا
    0.52
    ضی
    0.51
     PHA
    0.50
    اح
    0.50
     AGR
    0.50
     COPYRIGHT
    0.50
     amici
    0.50
    POSITIVE LOGITS
    II
    0.67
    quele
    0.66
    ១
    0.61
    ية
    0.58
    penas
    0.58
    an
    0.57
    ма
    0.57
    IO
    0.57
    lb
    0.57
    lashes
    0.57
    Activations Density 0.000%

    No Known Activations