© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116676
    Prev
    Next
    INDEX
    Explanations

    dataset or model names

    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
     これらの
    -0.06
     paraf
    -0.06
     distributed
    -0.06
     differing
    -0.06
     ผู้
    -0.06
     Returned
    -0.06
     ″
    -0.06
    distributed
    -0.06
     หมด
    -0.06
    Ethiop
    -0.06
    POSITIVE LOGITS
    하실
    0.07
     следующем
    0.06
     pesquisas
    0.06
     siguiente
    0.06
     haven
    0.06
     исследования
    0.06
    研究
    0.06
     siguientes
    0.06
     هيكون
    0.06
     penelitian
    0.06
    Activations Density 0.003%

    No Known Activations