© 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. 119159
    Prev
    Next
    INDEX
    Explanations

    links, URLs, or file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     while
    -0.06
    !!!!
    -0.06
    **(
    -0.06
     அதே
    -0.06
     (
    -0.06
    !!
    -0.05
    etrot
    -0.05
    Frontend
    -0.05
    !(
    -0.05
    하면서
    -0.05
    POSITIVE LOGITS
     for
    0.07
    可以是
    0.07
     czyli
    0.06
     послед
    0.06
     bây
    0.06
     एक
    0.06
    っぽい
    0.06
    अब
    0.06
     NYC
    0.06
    错了
    0.06
    Activations Density 0.005%

    No Known Activations