© 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. 11743
    Prev
    Next
    INDEX
    Explanations

    foul play or Joules

    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
    с
    2.63
    ف
    2.61
    č
    2.56
    ud
    2.39
    л
    2.39
    á
    2.39
    ॉन
    2.27
    udrait
    2.27
    <0xA1>
    2.17
    ł
    2.17
    POSITIVE LOGITS
     وعلى
    2.39
    casus
    1.84
    राणिक
    1.73
     genetically
    1.70
    ද්ග
    1.68
     intellectuals
    1.63
     protagonist
    1.63
     miraculously
    1.62
     phonons
    1.61
     immunoglobulin
    1.61
    Activations Density 0.284%

    No Known Activations