© 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. 117193
    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
     не
    -0.06
     对于
    -0.06
     означа
    -0.06
    等が
    -0.06
     特別
    -0.06
    などが
    -0.06
     koncert
    -0.06
     डेंटल
    -0.06
     நில
    -0.06
    交通
    -0.06
    POSITIVE LOGITS
     the
    0.07
    Cro
    0.07
    单独
    0.06
    tin
    0.06
     Cro
    0.06
     Al
    0.06
    Al
    0.06
    Tin
    0.06
    敷
    0.06
    all
    0.06
    Activations Density 0.000%

    No Known Activations