© 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. 116321
    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
     फॉलो
    -0.06
    ड्या
    -0.06
     नीचे
    -0.06
     follow
    -0.06
    מן
    -0.05
     Freshman
    -0.05
     Deutschland
    -0.05
    eniu
    -0.05
    पर
    -0.05
     KPI
    -0.05
    POSITIVE LOGITS
     consensual
    0.08
    自由
    0.08
     liberté
    0.07
     freely
    0.07
     awaiting
    0.07
     liberdade
    0.07
     consenso
    0.07
     lawfully
    0.07
     lawful
    0.07
     Protector
    0.06
    Activations Density 0.000%

    No Known Activations