© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118088
    Prev
    Next
    INDEX
    Explanations

    political alignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     banknote
    -0.07
    ليف
    -0.07
    Eight
    -0.06
    ※
    -0.06
     swoją
    -0.06
     Eight
    -0.06
     dù
    -0.06
     অভ্যন্তরীণ
    -0.06
     sauf
    -0.06
     最
    -0.06
    POSITIVE LOGITS
     independent
    0.08
     независи
    0.07
     indépend
    0.07
    独立的
    0.06
     independientes
    0.06
     independents
    0.06
    Independent
    0.06
    独立
    0.06
     Independent
    0.06
     अधिक
    0.06
    Activations Density 0.003%

    No Known Activations