© 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. 194234
    Prev
    Next
    INDEX
    Explanations

    getting high and sensitive information

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

    using machine

    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
     d
    0.50
     spies
    0.49
     heist
    0.49
     naps
    0.49
     watchdog
    0.48
     probl
    0.48
     quiz
    0.48
     from
    0.48
     www
    0.48
     spy
    0.48
    POSITIVE LOGITS
    ﺎ
    0.59
    ム
    0.57
    惋
    0.57
    ﮑ
    0.54
    Mg
    0.51
    vinced
    0.50
    ل
    0.49
    ಿಸ
    0.49
    苫
    0.48
    該
    0.47
    Activations Density 0.000%

    No Known Activations