© 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. 116583
    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
     unforeseen
    -0.06
     empfehlen
    -0.06
     වශ
    -0.06
     https
    -0.06
     hinder
    -0.06
     इंतजार
    -0.06
     Hickory
    -0.05
     quirky
    -0.05
    Upcoming
    -0.05
     frat
    -0.05
    POSITIVE LOGITS
    सबसे
    0.08
     schönsten
    0.06
     whak
    0.06
     руководи
    0.06
    쇤
    0.06
    aaaaaaaa
    0.06
     enhances
    0.06
     démont
    0.06
    ไม่ใช่
    0.06
     Whistler
    0.06
    Activations Density 0.000%

    No Known Activations