© 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. 84780
    Prev
    Next
    INDEX
    Explanations

    row, column, elimination, rank, swap

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

    swapping elements

    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
    ࿐
    0.40
    绵
    0.40
     áng
    0.39
    watercolor
    0.39
     Lösungen
    0.39
     annuelle
    0.39
    Solutions
    0.38
     rozwiąz
    0.38
    ঈ
    0.38
     batik
    0.38
    POSITIVE LOGITS
     swap
    0.54
     swapping
    0.52
     swapped
    0.52
    swap
    0.51
     Swap
    0.46
    交换
    0.46
     swaps
    0.46
    階段
    0.44
     row
    0.44
    交換
    0.43
    Activations Density 0.001%

    No Known Activations