© 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. 119317
    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
    เพิ่ม
    -0.06
    ನ್ನೂ
    -0.06
     habe
    -0.06
     그런
    -0.06
     উঠলাম
    -0.06
    新たに
    -0.06
     salesmen
    -0.06
     ভাল
    -0.06
     ancora
    -0.06
    সেই
    -0.06
    POSITIVE LOGITS
    উন
    0.07
     ufficiale
    0.06
     diversas
    0.06
     boyunca
    0.06
    专用
    0.06
     ადგილ
    0.06
     அதிகார
    0.06
     линии
    0.06
    න
    0.06
    Comparison
    0.06
    Activations Density 0.000%

    No Known Activations