© 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. 120250
    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
     evid
    -0.05
     ไว้
    -0.05
    চিত্র
    -0.05
    Buf
    -0.05
     ৬৫
    -0.05
     If
    -0.05
     sowohl
    -0.05
     nucleation
    -0.05
    ALWAYS
    -0.05
     соеди
    -0.05
    POSITIVE LOGITS
     určit
    0.07
     ಮತ್ತು
    0.06
    픈
    0.06
     conjuntos
    0.06
     herhangi
    0.06
     build
    0.06
    idaknya
    0.06
     گوئیاں
    0.06
    आख
    0.06
    ਡ
    0.06
    Activations Density 0.000%

    No Known Activations