© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118172
    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
     after
    -0.06
     pakaian
    -0.06
     после
    -0.06
    第七
    -0.06
    하고
    -0.06
    otro
    -0.06
    ాలని
    -0.06
    قدم
    -0.06
     نہیں
    -0.06
     espec
    -0.06
    POSITIVE LOGITS
     моём
    0.06
     இருப்பதால்
    0.06
     grotesque
    0.05
     murder
    0.05
     therefore
    0.05
    。”
    0.05
    uncur
    0.05
     hacen
    0.05
     Verw
    0.05
     Jawa
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.