© 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. 119483
    Prev
    Next
    INDEX
    Explanations

    leaders and leadership figures

    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
    かと思います
    -0.07
     winners
    -0.06
    あるいは
    -0.06
     reporters
    -0.06
    বেশী
    -0.06
    REPORT
    -0.06
    Lastly
    -0.06
    राल
    -0.06
     hurting
    -0.06
     journalists
    -0.06
    POSITIVE LOGITS
     ಅವರ
    0.07
     allowances
    0.06
     personalise
    0.06
     persönliche
    0.06
     persönlichen
    0.06
     जैसे
    0.06
    类型的
    0.06
     no
    0.06
     customize
    0.06
    个人的
    0.06
    Activations Density 0.018%

    No Known Activations