© 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. 128095
    Prev
    Next
    INDEX
    Explanations

    Pope election

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

    election, appointment, or coronation of leaders

    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
    uillez
    0.47
     कुमारी
    0.46
    idently
    0.46
    っております
    0.45
    ණ්ඩ
    0.42
     undeniably
    0.41
     undoubt
    0.41
    芡
    0.41
     enquiries
    0.41
    žia
    0.41
    POSITIVE LOGITS
     Prophets
    0.45
    incar
    0.45
    他們
    0.44
     collective
    0.44
     imprisoned
    0.43
     magicians
    0.43
     μπορού
    0.43
     magically
    0.42
    σμ
    0.42
     或
    0.41
    Activations Density 0.007%

    No Known Activations