© 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. 41-GEMMASCOPE-2-RES-262K
    7. 26557
    Prev
    Next
    INDEX
    Explanations

    construction scaffolding rigging

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uprising
    0.38
    cInfo
    0.36
     uprisings
    0.36
    dL
    0.36
     корпу
    0.34
     revolt
    0.34
    iyaki
    0.34
    渺
    0.34
     revol
    0.33
     Cinnamon
    0.33
    POSITIVE LOGITS
     scaffolding
    0.64
    Temporary
    0.57
     scaffold
    0.56
     scaffolds
    0.55
     temporary
    0.55
     Temporary
    0.55
     Scaffold
    0.52
    temporary
    0.51
     rigging
    0.46
    搭建
    0.45
    Activations Density 0.003%

    No Known Activations