© 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. 117886
    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
     también
    -0.07
     лучше
    -0.06
     latter
    -0.06
     jähr
    -0.06
     обоих
    -0.06
     também
    -0.06
     single
    -0.06
     två
    -0.06
     নিজেই
    -0.06
    aye
    -0.06
    POSITIVE LOGITS
     Alongside
    0.06
     σειρά
    0.06
     assuring
    0.06
    Rés
    0.06
     estratég
    0.06
     refrigeration
    0.06
     جاء
    0.06
     estratégico
    0.06
     vient
    0.06
     wherein
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.