© 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. 224566
    Prev
    Next
    INDEX
    Explanations

    geographic locations and transitions

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

    these directoriesconnecting systemsGovernment Shutdown

    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
     તમને
    0.45
    াচিত
    0.45
    বিত্র
    0.43
     piaci
    0.42
     উপহার
    0.41
    喜
    0.41
     kisses
    0.39
     Mandala
    0.39
     gelen
    0.39
     Psalm
    0.38
    POSITIVE LOGITS
    ごとに
    0.54
     доме
    0.53
    멧
    0.47
     пе
    0.47
    ㅁ
    0.47
    AID
    0.47
    (−
    0.46
    міна
    0.46
     усі
    0.46
     pcMove
    0.45
    Activations Density 0.001%

    No Known Activations