© 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. 119611
    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
     근
    -0.06
     गए
    -0.06
     которое
    -0.06
    끙
    -0.06
     मित्रा
    -0.06
     یخ
    -0.06
    ১৫
    -0.06
     dlatego
    -0.06
     buddh
    -0.06
    出手
    -0.06
    POSITIVE LOGITS
     যের
    0.06
     पालक
    0.05
    的话
    0.05
     അവരുടെ
    0.05
     scissors
    0.05
     बोलते
    0.05
     cias
    0.05
     enrich
    0.05
    ienced
    0.05
    TreeMap
    0.05
    Activations Density 0.000%

    No Known Activations