© 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. 119075
    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
     सही
    -0.07
    時に
    -0.06
     nějak
    -0.06
     அல்லது
    -0.06
     ወይም
    -0.06
     שי
    -0.06
     Работа
    -0.06
     학
    -0.06
     Cak
    -0.06
    cuando
    -0.06
    POSITIVE LOGITS
     replaces
    0.06
     Rv
    0.06
    buddy
    0.05
    fasc
    0.05
     قبول
    0.05
    꿉
    0.05
     vigorous
    0.05
     প্রিয়
    0.05
     replacing
    0.05
     predominantly
    0.05
    Activations Density 0.000%

    No Known Activations