© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 259567
    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
     occupation
    0.52
    ラー
    0.50
    ش
    0.48
    ق
    0.48
    ング
    0.48
     conscience
    0.48
    ܫ
    0.48
    ニュー
    0.47
    ノ
    0.47
    プロ
    0.47
    POSITIVE LOGITS
     为了
    0.63
     CtApp
    0.52
     定义
    0.52
     限定
    0.51
     Comenz
    0.51
     用于
    0.49
    ຂໍ້ມ
    0.49
     Streak
    0.49
     Unwrap
    0.47
     Elimin
    0.46
    Activations Density 0.001%

    No Known Activations