© 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. 118705
    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
     Veronica
    -0.06
     subcontinent
    -0.06
    ptica
    -0.06
     elucidate
    -0.06
    ombok
    -0.06
     ప్రజ
    -0.06
     τελευτα
    -0.06
     ختم
    -0.06
     টিম
    -0.05
     νέα
    -0.05
    POSITIVE LOGITS
     conocido
    0.07
     कॉमे
    0.06
    ทั่วไป
    0.06
    不
    0.06
     dut
    0.06
    これ
    0.06
    ..,
    0.06
    ,\,\,\,\
    0.06
    떄
    0.06
    Bread
    0.05
    Activations Density 0.000%

    No Known Activations