© 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. 129237
    Prev
    Next
    INDEX
    Explanations

    used for calculating squares

    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
     cient
    0.46
     especial
    0.42
     formerly
    0.41
    iggles
    0.41
    our
    0.38
     magnitude
    0.38
     remarkable
    0.38
     politica
    0.38
    sus
    0.38
     registered
    0.37
    POSITIVE LOGITS
     έως
    0.51
     ойноо
    0.46
    ویت
    0.44
     ☐
    0.43
     ресурсы
    0.42
    ञ्च
    0.41
     අවශ්‍ය
    0.41
     escritorio
    0.41
    𒈾
    0.41
     μία
    0.40
    Activations Density 0.002%

    No Known Activations