© 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. 119984
    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
     hurricane
    -0.06
    மையில்
    -0.06
     μεταξύ
    -0.06
    ignty
    -0.05
     приятно
    -0.05
     образова
    -0.05
     Gertrude
    -0.05
     stakeholders
    -0.05
    тей
    -0.05
     Hurricane
    -0.05
    POSITIVE LOGITS
     ordinairement
    0.07
     progresses
    0.06
    그리고
    0.06
     progressivement
    0.06
    _{-}^{
    0.06
     soms
    0.06
     differ
    0.06
    できない
    0.06
    aluminum
    0.06
     خواہش
    0.06
    Activations Density 0.000%

    No Known Activations