© 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. 130524
    Prev
    Next
    INDEX
    Explanations

    political party leadership and officials

    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
     ಔಷ
    -0.07
     enda
    -0.06
     constructed
    -0.06
     contribuer
    -0.06
     diferencial
    -0.06
    ^)
    -0.06
     অতিথ
    -0.06
    differential
    -0.06
     gunakan
    -0.06
     crafted
    -0.06
    POSITIVE LOGITS
     wspól
    0.07
    dynamics
    0.06
     gemeinsame
    0.06
     மூட
    0.06
     руководство
    0.06
    内部
    0.06
     birbir
    0.06
     communs
    0.05
     administrat
    0.05
     руковод
    0.05
    Activations Density 0.039%

    No Known Activations