© 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. 130539
    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
     prior
    -0.06
    考えて
    -0.05
    ূল
    -0.05
     மக்களை
    -0.05
    两人
    -0.05
    UMPS
    -0.05
    ISAM
    -0.05
    Before
    -0.05
    utes
    -0.05
    Two
    -0.05
    POSITIVE LOGITS
    無論
    0.07
     OTHERWISE
    0.06
     prawdopod
    0.06
    គឺជា
    0.06
     избира
    0.06
     Choisissez
    0.06
     sogen
    0.06
     питання
    0.06
     vorticity
    0.06
     पूर्णा
    0.06
    Activations Density 0.000%

    No Known Activations