© 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. 11695
    Prev
    Next
    INDEX
    Explanations

    natural gas

    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
    s
    2.23
    oretically
    1.72
    mselves
    1.70
    tä
    1.59
    ς
    1.57
    พ์
    1.55
    sı
    1.55
    nél
    1.47
    y
    1.46
    ्स
    1.45
    POSITIVE LOGITS
     and
    1.50
     outweigh
    1.38
     to
    1.33
    AR
    1.27
     craindre
    1.23
     specializing
    1.20
    alling
    1.18
    И
    1.17
    閱讀
    1.16
    ption
    1.16
    Activations Density 0.001%

    No Known Activations