© 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. 261031
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Advancement
    0.44
     Helpers
    0.44
    韵
    0.43
     Find
    0.42
     Advice
    0.42
     تضيف
    0.42
     DeepCollection
    0.42
     Wunder
    0.42
    竻
    0.42
     Extensions
    0.41
    POSITIVE LOGITS
     comrades
    0.44
    化
    0.44
    判定
    0.43
     سایر
    0.43
    }{
    0.42
     avenge
    0.42
    Others
    0.42
    ၠ
    0.42
    トラ
    0.42
     comrade
    0.42
    Activations Density 0.001%

    No Known Activations