© 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. 12578
    Prev
    Next
    INDEX
    Explanations

    political offices and entities

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

    government and political entities

    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
     设置
    0.57
     Mahogany
    0.57
     ή
    0.56
     Closure
    0.56
    达到
    0.55
     时
    0.54
    辊
    0.54
     Size
    0.53
    氩
    0.53
     Wetland
    0.53
    POSITIVE LOGITS
     politici
    0.91
     políticos
    0.84
     regering
    0.83
     gobiernos
    0.82
     правительства
    0.81
     governo
    0.80
     gobierno
    0.80
     statesmen
    0.79
     bureaucrats
    0.76
     guvern
    0.76
    Activations Density 0.106%

    No Known Activations