© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221086
    Prev
    Next
    INDEX
    Explanations

    anonymous communication, local network

    np_acts-logits-general · gemini-2.5-flash-lite

    introductory overviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     проекти
    0.50
     anderem
    0.48
     سایټ
    0.46
     جیسے
    0.46
     дви
    0.45
    鏗
    0.45
     capitalized
    0.45
    寯
    0.45
     фев
    0.44
    мовір
    0.44
    POSITIVE LOGITS
     tile
    0.44
     nurses
    0.43
     shuttle
    0.43
    0.42
     reeds
    0.42
    ode
    0.42
     tiles
    0.42
     théra
    0.41
     rows
    0.40
    教师
    0.39
    Activations Density 0.001%

    No Known Activations