© 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. 640
    Prev
    Next
    INDEX
    Explanations

    Japanese to English proficiency

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

    do it

    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
    ot
    1.23
    os
    1.22
    ai
    1.13
    et
    1.12
    us
    1.05
    ER
    1.05
    um
    0.99
     be
    0.98
    ৫
    0.98
     been
    0.95
    POSITIVE LOGITS
    ان
    1.08
    یل
    1.05
    ين
    1.02
    ون
    1.02
    ية
    1.01
    ə
    0.99
    ки
    0.96
    した
    0.93
     estrict
    0.93
    پ
    0.92
    Activations Density 1.501%

    No Known Activations