© 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. 131024
    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
     быстро
    -0.07
     trước
    -0.07
    一些
    -0.07
     durante
    -0.07
    तरा
    -0.07
    ١
    -0.06
     selama
    -0.06
     sechs
    -0.06
     unil
    -0.06
     decept
    -0.06
    POSITIVE LOGITS
    ).
    0.06
    %).
    0.06
     zvuk
    0.06
     socialism
    0.06
     tackling
    0.06
     gracias
    0.06
     সামগ্র
    0.05
    }.
    0.05
     पद्ध
    0.05
    '),
    0.05
    Activations Density 0.000%

    No Known Activations