© 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. 33884
    Prev
    Next
    INDEX
    Explanations

    Ocean Hills Recovery Center

    np_acts-logits-general · gemini-2.5-flash-lite

    logic and assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Españ
    0.49
     accanto
    0.46
     outpouring
    0.46
     Namun
    0.44
     kuiten
    0.42
     extol
    0.42
     altri
    0.41
     酸
    0.41
     袋
    0.41
     towering
    0.41
    POSITIVE LOGITS
    为
    0.59
    逻辑
    0.57
    赋值
    0.54
     =
    0.49
    =$
    0.48
    则
    0.47
    应该
    0.45
     함수
    0.45
    同样
    0.45
    比例
    0.45
    Activations Density 0.000%

    No Known Activations