© 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. 128818
    Prev
    Next
    INDEX
    Explanations

    structs, arrays, and memory allocation

    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
     riusc
    -0.06
    ParentElement
    -0.06
     مشتر
    -0.06
    inalis
    -0.06
     const
    -0.06
    主要
    -0.06
     hơi
    -0.06
     apart
    -0.06
     manifolds
    -0.05
    前半
    -0.05
    POSITIVE LOGITS
     fitur
    0.06
    iatric
    0.06
     peł
    0.06
     высоким
    0.06
     আচরণ
    0.06
     Fallon
    0.06
    是一位
    0.06
    obtenir
    0.06
     danni
    0.06
    र्सन
    0.06
    Activations Density 0.061%

    No Known Activations