© 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. 9327
    Prev
    Next
    INDEX
    Explanations

    allow plus following word

    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
     अधिकारों
    0.54
    rights
    0.49
    doctrine
    0.49
    MLElement
    0.48
    理
    0.48
    ට්ට
    0.47
    あなたは
    0.47
    锗
    0.46
    锑
    0.46
    权利
    0.46
    POSITIVE LOGITS
     লোক
    0.49
     Seda
    0.46
    awan
    0.45
    鳩
    0.45
    ทุกคน
    0.44
    makeText
    0.43
     Harus
    0.43
    asctime
    0.43
    jede
    0.43
    4
    0.43
    Activations Density 0.008%

    No Known Activations