© 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. 16-GEMMASCOPE-2-RES-262K
    7. 49691
    Prev
    Next
    INDEX
    Explanations

    compose.ui

    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_16_width_262k_l0_medium
    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
    ッティング
    0.53
    FilesIn
    0.46
    Plain
    0.46
    formas
    0.46
    ρούν
    0.44
    苻
    0.44
    ppen
    0.43
    mathfrak
    0.43
    Ren
    0.43
    MMC
    0.43
    POSITIVE LOGITS
     expand
    0.59
     certify
    0.58
    是
    0.56
    cı
    0.55
     tighten
    0.55
     số
    0.54
     denote
    0.54
    не
    0.53
     khác
    0.53
     gjøre
    0.52
    Activations Density 0.000%

    No Known Activations