© 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. 130938
    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
    सायनिक
    -0.06
     judicious
    -0.06
     ANOVA
    -0.06
     diferenci
    -0.06
    ក់
    -0.06
     ذہن
    -0.06
     জাপ
    -0.06
     ascorbic
    -0.06
     świad
    -0.06
    这一切
    -0.06
    POSITIVE LOGITS
     في
    0.06
    ,*
    0.06
     alba
    0.06
    就可以
    0.06
     entendido
    0.06
     famed
    0.06
     stesso
    0.05
     même
    0.05
     م
    0.05
    amed
    0.05
    Activations Density 0.000%

    No Known Activations