© 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. 16-GEMMASCOPE-2-RES-16K
    7. 744
    Prev
    Next
    INDEX
    Explanations

    spam driven

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

    trick question

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    is
    0.90
    it
    0.84
    ле
    0.79
    ال
    0.77
    να
    0.75
    ра
    0.71
    س
    0.70
    ad
    0.67
    бо
    0.67
    ме
    0.67
    POSITIVE LOGITS
    ’
    0.91
    -
    0.83
    ↵
    0.81
     écart
    0.77
     jeopard
    0.76
     welches
    0.68
     catheters
    0.66
    DI
    0.64
     adı
    0.63
     cheating
    0.63
    Activations Density 1.992%

    No Known Activations