© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9722
    Prev
    Next
    INDEX
    Explanations

    divide by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    0.54
     omkring
    0.52
     jogos
    0.51
     ausger
    0.50
     أف
    0.49
     घंटों
    0.49
     vaiht
    0.49
     eingeb
    0.48
    钢琴
    0.48
     奥
    0.48
    POSITIVE LOGITS
     dividing
    1.06
     divide
    1.00
     나누
    0.98
     divisão
    0.95
     разделить
    0.94
     Dividing
    0.93
    Divid
    0.92
     divided
    0.91
     podziel
    0.91
     division
    0.90
    Activations Density 0.049%

    No Known Activations