© 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. 243699
    Prev
    Next
    INDEX
    Explanations

    completion or exit

    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
    伫
    0.40
    émie
    0.38
     beliefs
    0.38
    势力
    0.38
    बानी
    0.37
     traumas
    0.37
    盪
    0.37
     median
    0.37
     shocks
    0.37
     ขณะ
    0.37
    POSITIVE LOGITS
    退出
    0.89
     return
    0.82
    終了
    0.82
     واپسی
    0.80
    结束后
    0.80
    戻
    0.79
     exit
    0.79
     RETURN
    0.79
     Exit
    0.77
     logout
    0.77
    Activations Density 0.202%

    No Known Activations