© 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. 30448
    Prev
    Next
    INDEX
    Explanations

    country names and ambassadors

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

    nationalities and demonyms

    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
    его
    0.41
    është
    0.39
    vertices
    0.38
    То
    0.38
    ChangeString
    0.38
    🪴
    0.38
    Ха
    0.38
    Аль
    0.38
    {|
    0.38
    Со
    0.38
    POSITIVE LOGITS
     IAAF
    0.44
     appointed
    0.43
     ambas
    0.43
     aux
    0.41
     আপনাকে
    0.41
     Counsel
    0.41
     Liaison
    0.40
     ambos
    0.40
     नियुक्त
    0.40
     unborn
    0.40
    Activations Density 0.000%

    No Known Activations