© 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. 220119
    Prev
    Next
    INDEX
    Explanations

    reading CSV files

    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
     framework
    0.48
    DataFrame
    0.46
     pandas
    0.44
     DataFrame
    0.44
     frameworks
    0.43
     panda
    0.43
    йл
    0.42
    dataframe
    0.41
     Framework
    0.41
    枠
    0.41
    POSITIVE LOGITS
     Bottles
    0.46
     उपयोगी
    0.45
     शर्त
    0.42
    ipore
    0.41
     النرويج
    0.40
     буты
    0.40
     másc
    0.40
     Drops
    0.40
     Cline
    0.40
     bottles
    0.39
    Activations Density 0.018%

    No Known Activations