© 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. 128891
    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
    ouard
    -0.06
     efectuar
    -0.06
     আশ্চর্যজনক
    -0.06
     வழங்கும்
    -0.05
     роки
    -0.05
    mover
    -0.05
    他に
    -0.05
     ನಡೆದ
    -0.05
    Motivational
    -0.05
     Such
    -0.05
    POSITIVE LOGITS
     più
    0.07
    ㄛ
    0.06
    ारखंड
    0.06
     vegetable
    0.06
     כש
    0.06
     শেখ
    0.06
     trespass
    0.06
     rust
    0.06
     pärast
    0.06
    ตอนนี้
    0.06
    Activations Density 0.000%

    No Known Activations