© 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. 9650
    Prev
    Next
    INDEX
    Explanations

    new leader or owner

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

    succession or new beginning

    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
    越来越
    0.45
     altid
    0.43
     saepe
    0.42
     glab
    0.41
     থাকে
    0.40
     sourceL
    0.39
     pouce
    0.38
    )=$
    0.38
    farande
    0.37
     आजही
    0.37
    POSITIVE LOGITS
     inheriting
    0.84
     übernommen
    0.80
     nowego
    0.79
     новой
    0.78
     inherits
    0.77
     inherited
    0.76
     nieuwe
    0.75
     нового
    0.75
     новом
    0.75
     incoming
    0.73
    Activations Density 0.208%

    No Known Activations