© 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. 259064
    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
    你
    0.54
    波
    0.54
    印度
    0.53
    线性
    0.52
    司法
    0.50
    <sup>
    0.49
    두
    0.48
    你需要
    0.47
    คุณ
    0.47
    \
    0.47
    POSITIVE LOGITS
    c
    0.53
    o
    0.51
     کریں۔
    0.50
     Comprom
    0.50
     comprom
    0.50
     compromise
    0.47
     ዋ
    0.47
     これは
    0.47
     Period
    0.46
     consist
    0.45
    Activations Density 0.001%

    No Known Activations