© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 4776
    Prev
    Next
    INDEX
    Explanations

    archaic language

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    1
    1.50
    s
    1.24
     There
    1.23
    ad
    1.16
    b
    1.16
     and
    1.14
     It
    1.12
    et
    1.11
     a
    1.08
    c
    1.08
    POSITIVE LOGITS
    ও
    1.09
    も
    1.07
    もら
    0.92
     یورو
    0.89
    도
    0.86
    padă
    0.86
    ﺭ
    0.85
     ಸಂಧಿ
    0.83
     ಹಲವಾರು
    0.82
     في
    0.79
    Activations Density 0.361%

    No Known Activations