© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 232659
    Prev
    Next
    INDEX
    Explanations

    political concepts

    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
    ;
    0.47
    ắc
    0.44
     Retro
    0.44
     사용하여
    0.43
     Groove
    0.43
     Gummies
    0.42
    ethyst
    0.42
     mainly
    0.42
     Discord
    0.42
     Sph
    0.41
    POSITIVE LOGITS
     полити
    0.54
    政治
    0.53
    壟
    0.53
     zahrani
    0.52
     وزير
    0.51
     национа
    0.50
     രാജ്യ
    0.48
     politische
    0.46
    political
    0.46
     عصر
    0.46
    Activations Density 0.000%

    No Known Activations