© 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. 261169
    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
     生命
    0.55
     ベッド
    0.55
    ლებიც
    0.54
     Казіно
    0.52
     অগ্রগতি
    0.52
    eneva
    0.52
     ゆっくり
    0.52
     Antennes
    0.50
    lk
    0.50
    <unused41>
    0.50
    POSITIVE LOGITS
     Iss
    0.48
    s
    0.47
    का
    0.46
    对
    0.46
     They
    0.46
     Form
    0.46
    ی
    0.45
     blir
    0.44
    성
    0.44
     Jacobian
    0.44
    Activations Density 0.001%

    No Known Activations