© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130719
    Prev
    Next
    INDEX
    Explanations

    mom or listing moms

    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
     също
    -0.07
     kiezen
    -0.06
     acess
    -0.06
    violet
    -0.06
     wybrać
    -0.06
     reaffirm
    -0.06
    퀴
    -0.06
     бонус
    -0.06
     etik
    -0.06
    Christ
    -0.06
    POSITIVE LOGITS
    ราย
    0.07
     at
    0.06
     desgr
    0.06
     ஒருவர்
    0.06
     pala
    0.06
     on
    0.06
    ാല്‍
    0.06
     কখনোই
    0.06
    renched
    0.05
     على
    0.05
    Activations Density 0.004%

    No Known Activations