© 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. 118980
    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
    ँव
    -0.06
     সেসব
    -0.06
     свобод
    -0.06
    ရ
    -0.06
    朮
    -0.06
     personalità
    -0.05
     révolution
    -0.05
     simulated
    -0.05
     ספר
    -0.05
     familiare
    -0.05
    POSITIVE LOGITS
     ആദ്യം
    0.06
     ten
    0.06
     não
    0.06
     first
    0.06
     firstly
    0.06
     twenty
    0.06
    मार्
    0.06
    plante
    0.06
     μέσω
    0.06
    erus
    0.06
    Activations Density 0.000%

    No Known Activations