© 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. 117276
    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
     parfaitement
    -0.07
       
    -0.07
     :
    -0.06
     где
    -0.06
     ഉത്സ
    -0.06
     where
    -0.06
    sprogram
    -0.06
     dimana
    -0.06
     donde
    -0.06
     ;
    -0.06
    POSITIVE LOGITS
    あるいは
    0.07
     ಅಥವಾ
    0.07
     یا
    0.07
     or
    0.06
     leiden
    0.06
     ある
    0.06
     లేదా
    0.06
     dubbed
    0.06
     inher
    0.06
    atha
    0.06
    Activations Density 0.000%

    No Known Activations