© 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. 129181
    Prev
    Next
    INDEX
    Explanations

    Mayor, consul, senator

    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
     modernize
    -0.07
    modification
    -0.06
     înd
    -0.06
     disagreements
    -0.06
    修改
    -0.06
     Appet
    -0.06
    改
    -0.06
     downwards
    -0.06
     restructure
    -0.06
     modifica
    -0.06
    POSITIVE LOGITS
     annual
    0.08
     prominently
    0.07
    全年
    0.07
    annual
    0.07
     annuelle
    0.07
     annually
    0.06
     checklist
    0.06
     Annual
    0.06
     circle
    0.06
    Annual
    0.06
    Activations Density 0.004%

    No Known Activations