© 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. 117870
    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
    maximal
    -0.06
     maximal
    -0.06
     conse
    -0.06
     उपहार
    -0.06
     Month
    -0.06
    carousel
    -0.06
     plenty
    -0.05
     it
    -0.05
    其
    -0.05
     সমগ্র
    -0.05
    POSITIVE LOGITS
     нарко
    0.07
     THEY
    0.06
    हे
    0.06
    現在の
    0.06
     ricerca
    0.06
     និង
    0.06
    也
    0.06
     چنین
    0.06
    ̾
    0.06
    était
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.