© 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. 128369
    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
     currants
    -0.07
     unsurprisingly
    -0.06
     mucho
    -0.06
    much
    -0.06
    铆
    -0.06
     Partially
    -0.06
     overdraft
    -0.06
    longer
    -0.06
     Version
    -0.06
     supremacist
    -0.06
    POSITIVE LOGITS
     доктор
    0.06
     hoeveel
    0.06
     গাঙ্গুল
    0.06
     neurotrans
    0.06
     JLabel
    0.06
     እንደሚ
    0.06
     kişinin
    0.06
    iende
    0.06
    [],
    0.05
     منطقه
    0.05
    Activations Density 0.000%

    No Known Activations