© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119381
    Prev
    Next
    INDEX
    Explanations

    party leader or legislator

    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
    orpio
    -0.06
     পুরাতন
    -0.06
     Definitely
    -0.06
     constantly
    -0.06
     thinker
    -0.05
    基本的に
    -0.05
    Definitely
    -0.05
     static
    -0.05
     slander
    -0.05
     எப்போதும்
    -0.05
    POSITIVE LOGITS
     presiden
    0.07
     Joseph
    0.07
     president
    0.07
     weitere
    0.07
     chỉ
    0.07
     यूज
    0.07
     zaht
    0.06
     only
    0.06
     лишь
    0.06
     सहित
    0.06
    Activations Density 0.015%

    No Known Activations