© 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. 119696
    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
     برخی
    -0.06
     दूरसंचार
    -0.06
     beetje
    -0.06
     तुमने
    -0.06
     मौजूदा
    -0.06
    hre
    -0.06
     bazı
    -0.06
     일부
    -0.06
     några
    -0.06
     क्षेत्रफल
    -0.06
    POSITIVE LOGITS
    \*
    0.06
    àu
    0.06
     इतर
    0.06
    ↵↵
    0.06
    Local
    0.05
     is
    0.05
     victoria
    0.05
     inicio
    0.05
    other
    0.05
    分けて
    0.05
    Activations Density 0.000%

    No Known Activations