© 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. 119910
    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
     मुंबई
    -0.06
     finanzi
    -0.06
     सपोर्ट
    -0.06
     JC
    -0.06
     কল্প
    -0.06
     wrought
    -0.06
    用餐
    -0.06
     यादगार
    -0.06
     damals
    -0.06
     पोर्ट
    -0.06
    POSITIVE LOGITS
     Анаста
    0.07
    তবে
    0.06
     或
    0.06
    possessed
    0.06
     தய
    0.06
     pertenecen
    0.06
    Promise
    0.06
    plants
    0.05
     Gesamt
    0.05
     அருள்
    0.05
    Activations Density 0.000%

    No Known Activations