© 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. 778
    Prev
    Next
    INDEX
    Explanations

    medical dosages and years

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

    year, date, and numerical values

    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
     of
    1.67
    of
    1.41
     for
    1.32
    ע
    1.10
        
    1.01
     T
    1.00
    m
    0.97
    ס
    0.96
     M
    0.95
     \
    0.94
    POSITIVE LOGITS
    ல்
    1.11
    ми
    1.09
    ших
    1.01
    ко
    0.98
    зыва
    0.95
    ской
    0.93
    きる
    0.91
    луйста
    0.89
     osobe
    0.89
     are
    0.88
    Activations Density 0.548%

    No Known Activations