© 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. 738
    Prev
    Next
    INDEX
    Explanations

    digits like 7 or 9

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

    numbers, dosages, people

    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
    t
    0.82
     (
    0.80
    не
    0.66
    եմ
    0.66
    ει
    0.65
    。
    0.63
    ीकृत
    0.62
     experimentado
    0.61
    і
    0.61
    𝐭
    0.61
    POSITIVE LOGITS
     for
    1.05
     in
    1.00
    ↵
    0.92
    在
    0.89
    at
    0.85
    TO
    0.82
    Have
    0.78
     در
    0.76
    RE
    0.73
     في
    0.73
    Activations Density 0.651%

    No Known Activations