© 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-262K
    7. 34544
    Prev
    Next
    INDEX
    Explanations

    polynomial time and equations

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    то
    1.41
     assh
    1.41
     asshole
    1.37
     littoral
    1.36
     altra
    1.31
     medico
    1.30
     aunt
    1.28
     athe
    1.28
    р
    1.28
     stato
    1.27
    POSITIVE LOGITS
    s
    3.56
    ्स
    2.47
    س
    2.14
    ের
    2.11
    ことにより
    2.11
    ことなく
    2.03
    ことが多い
    2.00
    ação
    1.97
    ς
    1.92
    ことが
    1.91
    Activations Density 0.003%

    No Known Activations