© 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. 19754
    Prev
    Next
    INDEX
    Explanations

    Democratic and Republican parties

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

    political parties and affiliation

    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
     ห้อง
    0.52
     nitrite
    0.50
     produktów
    0.49
     części
    0.48
     আঘাত
    0.46
    মিক্যাল
    0.46
     proteinuria
    0.45
    ၆
    0.45
    空气
    0.45
     himself
    0.45
    POSITIVE LOGITS
     Party
    0.91
    黨
    0.91
    Party
    0.83
     పార్టీ
    0.83
     партия
    0.80
     پارٹی
    0.79
    党
    0.79
     PARTY
    0.78
     party
    0.77
    PARTY
    0.76
    Activations Density 0.075%

    No Known Activations