© 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. 117173
    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
     मामूली
    -0.08
     parece
    -0.07
     স্ট
    -0.06
     coś
    -0.06
     the
    -0.06
    াম
    -0.06
    ,,,,
    -0.06
     ..............
    -0.06
     manche
    -0.06
     ..........
    -0.06
    POSITIVE LOGITS
     future
    0.06
    未来
    0.06
     pouvant
    0.06
     sẽ
    0.06
     অসুস্থ
    0.06
     birbirinden
    0.06
     любой
    0.05
    ToAdd
    0.05
     futuros
    0.05
    今後
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.