© 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. 24996
    Prev
    Next
    INDEX
    Explanations

    Shadow Minister or Opposition Leader

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

    political leaders and opposition figures

    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
    意见
    0.43
    řed
    0.41
     жидкости
    0.40
    >∈</
    0.39
     религи
    0.39
    岀
    0.38
    надцать
    0.38
    য়
    0.38
    盉
    0.38
    属于
    0.37
    POSITIVE LOGITS
     Opposition
    0.50
     líder
    0.45
     opposition
    0.45
    Opposition
    0.45
    shadow
    0.44
     Leader
    0.43
     দলের
    0.43
     Cadillac
    0.43
     oposición
    0.43
     Oppo
    0.43
    Activations Density 0.043%

    No Known Activations