© 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. 39221
    Prev
    Next
    INDEX
    Explanations

    political system

    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
     час
    0.53
    anız
    0.50
     санти
    0.50
     чыныгы
    0.50
    犄
    0.47
     человек
    0.47
     것은
    0.47
    ке
    0.47
    วรร
    0.46
     Вікіпедії
    0.46
    POSITIVE LOGITS
     phospholipids
    0.54
     pigments
    0.51
    ,
    0.51
     selenium
    0.51
     titers
    0.50
     extensively
    0.49
     covalently
    0.49
     secreted
    0.48
     antibodies
    0.48
     glutathione
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.