© 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. 119961
    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
    旗
    -0.06
     [
    -0.06
     the
    -0.06
     (
    -0.06
    new
    -0.06
    ah
    -0.06
    .
    -0.06
    extent
    -0.06
    hat
    -0.05
    jem
    -0.05
    POSITIVE LOGITS
     breathtaking
    0.07
    lässlich
    0.07
     יותר
    0.07
     알아보
    0.06
     vicenda
    0.06
     reprieve
    0.06
    区别
    0.06
     ursprünglich
    0.06
     seldom
    0.06
     consisting
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.