© 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. 220706
    Prev
    Next
    INDEX
    Explanations

    shutting down Windows 10 over Remote Desktop

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

    label affect skill Google know questions Water Windows

    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
    ä
    0.63
    ס
    0.47
    ె
    0.45
    ättre
    0.44
    Replacing
    0.44
     Prefer
    0.43
    Wouldn
    0.43
    嶈
    0.43
    庤
    0.43
     Wouldn
    0.42
    POSITIVE LOGITS
     afuera
    0.49
    miş
    0.48
    കം
    0.48
     distinta
    0.48
     fuera
    0.47
     Sada
    0.47
     wọn
    0.47
     kriy
    0.46
     kendisine
    0.46
     SELF
    0.45
    Activations Density 0.000%

    No Known Activations