© 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. 118955
    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
    でしたが
    -0.06
    ത്തിന്
    -0.06
     Кроме
    -0.06
     hingga
    -0.06
     व्यापक
    -0.06
     Además
    -0.06
     Thanh
    -0.06
     types
    -0.06
     insisted
    -0.05
    试验
    -0.05
    POSITIVE LOGITS
    IZATION
    0.06
     selben
    0.06
    GAS
    0.06
     gestalten
    0.06
     guérison
    0.06
     valide
    0.06
     বাসিন্দ
    0.06
     thousands
    0.05
    ங்களும்
    0.05
    ancourt
    0.05
    Activations Density 0.000%

    No Known Activations