© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2
    Prev
    Next
    INDEX
    Explanations

    probability or function calls

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     természet
    0.62
    ナソニック
    0.61
    ﺽ
    0.61
    <unused32>
    0.60
     -"
    0.59
     constituye
    0.58
     えっと
    0.57
     بیاکت
    0.57
     بیاکتنې
    0.57
     estabelecer
    0.56
    POSITIVE LOGITS
    (
    2.83
     (
    2.50
    （
    2.11
    ((
    1.77
    (\
    1.66
    ([
    1.62
    ($
    1.58
    (@
    1.52
    ("
    1.48
    ({
    1.48
    Activations Density 1.090%

    No Known Activations