© 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. 116849
    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
     আপাত
    -0.06
    THIS
    -0.06
     egyszerű
    -0.06
     BUSINESS
    -0.06
     एवरी
    -0.06
     جميل
    -0.06
    தியின்
    -0.06
     DETAILS
    -0.05
     oppervlak
    -0.05
     Rated
    -0.05
    POSITIVE LOGITS
     ofte
    0.06
     ofta
    0.06
    langen
    0.06
     знаете
    0.06
     displayed
    0.06
     Keto
    0.06
     Noël
    0.05
     piens
    0.05
    larla
    0.05
     usually
    0.05
    Activations Density 0.000%

    No Known Activations