© 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. 130291
    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
     خاصة
    -0.07
     innych
    -0.07
     drugih
    -0.06
    nbs
    -0.06
     but
    -0.06
     to
    -0.06
     अच्छे
    -0.06
     bunların
    -0.06
     précédents
    -0.06
    を
    -0.06
    POSITIVE LOGITS
     不
    0.06
     prilikom
    0.06
     मुसीबत
    0.06
     stutter
    0.06
     perilous
    0.06
     ہے
    0.06
     没有
    0.06
    凭借
    0.06
     não
    0.06
     употреб
    0.06
    Activations Density 0.000%

    No Known Activations