© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130419
    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
    felt
    -0.06
     Muir
    -0.06
    ボード
    -0.06
     değişken
    -0.06
    (-(
    -0.05
    Board
    -0.05
     chilled
    -0.05
     मिली
    -0.05
     hulle
    -0.05
     họ
    -0.05
    POSITIVE LOGITS
    匂
    0.07
     rezult
    0.07
     pretended
    0.06
     Nachrichten
    0.06
    bout
    0.06
     vervolgens
    0.06
     pretending
    0.06
     Ergebnis
    0.06
     phony
    0.06
    dry
    0.05
    Activations Density 0.000%

    No Known Activations