© 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. 117543
    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
    Neces
    -0.07
     Armour
    -0.06
    我们需要
    -0.06
     foss
    -0.06
     binoculars
    -0.06
     exponents
    -0.06
     needed
    -0.06
    硯
    -0.06
    နည်း
    -0.06
     sniper
    -0.06
    POSITIVE LOGITS
     чего
    0.07
     supervisor
    0.06
     surprises
    0.06
     carrot
    0.06
     surprise
    0.06
    当日
    0.06
    jol
    0.06
     персонала
    0.06
     После
    0.06
     contractual
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.