© 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. 128378
    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
    :
    -0.07
    ����
    -0.06
    ন্থা
    -0.06
     
    -0.06
     time
    -0.06
     users
    -0.06
    贈り物
    -0.05
    //
    -0.05
     commonplace
    -0.05
    📚
    -0.05
    POSITIVE LOGITS
     другая
    0.08
     какая
    0.07
     другой
    0.07
     ANY
    0.07
     weitere
    0.06
     называется
    0.06
     wäre
    0.06
     Any
    0.06
     And
    0.06
    weichen
    0.06
    Activations Density 0.000%

    No Known Activations