© 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. 120605
    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
     but
    -0.07
     लेकिन
    -0.06
     kõr
    -0.06
    Despite
    -0.06
     nhưng
    -0.06
     व्यापारियों
    -0.06
    %,
    -0.06
    respected
    -0.06
    但我
    -0.06
     সুষ্ঠ
    -0.06
    POSITIVE LOGITS
     Aliens
    0.06
     طریقہ
    0.06
     Behavioral
    0.06
     सांस
    0.06
    🛰
    0.06
     生
    0.05
     হঠাৎ
    0.05
     لگتا
    0.05
     affords
    0.05
    市民
    0.05
    Activations Density 0.000%

    No Known Activations