© 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. 128466
    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
     racines
    -0.07
     мой
    -0.07
     autoch
    -0.07
     mijn
    -0.06
    ིས་
    -0.06
     имеет
    -0.06
     dovol
    -0.06
     Bởi
    -0.06
    ittance
    -0.06
     delante
    -0.06
    POSITIVE LOGITS
     langsung
    0.07
     they
    0.06
    They
    0.06
     आठवीं
    0.06
     pihaknya
    0.06
    Compare
    0.05
    谱
    0.05
    在他
    0.05
    其它
    0.05
     directamente
    0.05
    Activations Density 0.000%

    No Known Activations