© 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. 118111
    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
     prolonged
    -0.07
    persistent
    -0.06
     मोठे
    -0.06
     তাড়াতাড়ি
    -0.06
     失
    -0.06
     LOST
    -0.06
     dłu
    -0.06
     satisfactorily
    -0.06
    urable
    -0.06
     favorables
    -0.06
    POSITIVE LOGITS
     before
    0.07
     Before
    0.07
     перед
    0.07
    Перед
    0.07
     ก่อน
    0.07
     ennen
    0.07
    Before
    0.06
    before
    0.06
    Sebelum
    0.06
    قبل
    0.06
    Activations Density 0.000%

    No Known Activations