© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6412
    Prev
    Next
    INDEX
    Explanations

    irmingham

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ’
    1.47
    ه‌
    1.45
    ั
    1.39
    ార్
    1.34
     कुर्ता
    1.33
    ことが多い
    1.30
     وعلى
    1.29
     dáng
    1.26
    ায়
    1.25
     térm
    1.25
    POSITIVE LOGITS
    an
    2.22
    se
    1.91
    ne
    1.80
    miri
    1.73
    n
    1.71
    speople
    1.70
    Diamonds
    1.70
    ra
    1.68
    m
    1.67
    stead
    1.66
    Activations Density 0.100%

    No Known Activations