© 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. 120600
    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
     almeno
    -0.06
     جاء
    -0.06
    決して
    -0.06
    โรง
    -0.06
     umfass
    -0.06
    !
    -0.06
     purchase
    -0.06
    !]
    -0.06
    あなた
    -0.06
     read
    -0.06
    POSITIVE LOGITS
     exporter
    0.06
     বেশির
    0.06
     szok
    0.06
    Exports
    0.06
     মৌসুম
    0.06
     oceans
    0.06
     repertoire
    0.06
     opsi
    0.06
     paucity
    0.06
     warmth
    0.06
    Activations Density 0.001%

    No Known Activations