© 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. 118627
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     стратегия
    -0.07
     எப்படி
    -0.06
     täglich
    -0.06
     sluč
    -0.06
     जुनून
    -0.06
     rezultat
    -0.06
     vẫn
    -0.06
     ১০০
    -0.06
     dono
    -0.06
     výkon
    -0.06
    POSITIVE LOGITS
    ?
    0.06
     at
    0.06
     would
    0.06
    เข้าร
    0.06
     molding
    0.06
    ,
    0.06
     অন্তত
    0.06
    rom
    0.06
    नरी
    0.06
    to
    0.06
    Activations Density 0.000%

    No Known Activations