© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3535
    Prev
    Next
    INDEX
    Explanations

    comes from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    럿
    0.67
    광역시
    0.66
    엄
    0.64
    zhang
    0.63
    Соцмережа
    0.61
    illow
    0.59
     Кы
    0.59
     серьез
    0.58
    Ձ
    0.58
     komm
    0.57
    POSITIVE LOGITS
     fruition
    0.71
    ছা
    0.66
    不及
    0.64
     Naturally
    0.62
     together
    0.61
     вместе
    0.61
    ตรฐาน
    0.58
     össze
    0.57
     Deputies
    0.57
     Benefits
    0.56
    Activations Density 0.205%

    No Known Activations