© 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. 261179
    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
    Negative Logits
     منفی
    0.51
    ኞች
    0.47
     계
    0.46
     Казах
    0.46
    筐
    0.46
    骊
    0.46
     జరిగ
    0.45
     गारंटर
    0.45
     नामा
    0.44
     मिरर
    0.44
    POSITIVE LOGITS
     Immaculate
    0.46
     cabelos
    0.46
    ر
    0.46
    ’,
    0.45
     Provinc
    0.44
     Antip
    0.44
    েন্ট
    0.44
    ียร์
    0.44
    ركة
    0.43
     ARC
    0.43
    Activations Density 0.001%

    No Known Activations