© 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. 40-GEMMASCOPE-2-RES-262K
    7. 135283
    Prev
    Next
    INDEX
    Explanations

    language and computing terms

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     roaring
    0.40
     incompar
    0.40
     inapplicable
    0.39
     clás
    0.38
     obnoxious
    0.38
     complacent
    0.38
     asymptotics
    0.38
     فى
    0.38
     无
    0.38
    bitos
    0.37
    POSITIVE LOGITS
     Resources
    0.39
     berita
    0.38
    www
    0.37
     Produced
    0.37
    language
    0.37
    ..."
    0.36
    导致
    0.36
     pozost
    0.35
     Specialist
    0.35
     খর
    0.35
    Activations Density 0.001%

    No Known Activations