© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 171862
    Prev
    Next
    INDEX
    Explanations

    mosquitoes bite

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

    Okay, instead, or

    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
    Negative Logits
     događ
    0.53
     مشاهد
    0.48
     moest
    0.48
    шње
    0.47
     errores
    0.46
     transacción
    0.46
     gă
    0.46
     izvor
    0.46
    맇
    0.46
     errori
    0.45
    POSITIVE LOGITS
     underage
    0.47
     Commissioner
    0.46
     manners
    0.45
     inflated
    0.43
     promotion
    0.40
     Buddhist
    0.40
     respectful
    0.40
     ہی
    0.39
    ード
    0.39
    nette
    0.39
    Activations Density 0.000%

    No Known Activations