© 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. 130398
    Prev
    Next
    INDEX
    Explanations

    tab or tabs with following context

    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
    Transit
    -0.06
     विकार
    -0.06
    Can
    -0.06
     desarrolló
    -0.06
     разработан
    -0.06
     depositors
    -0.06
     Director
    -0.06
     руководителя
    -0.06
    馨
    -0.06
    .),
    -0.05
    POSITIVE LOGITS
     spont
    0.07
    respectively
    0.06
    basename
    0.06
     espont
    0.06
    高性能
    0.06
    ‮
    0.06
     संभव
    0.06
     folgende
    0.06
     laki
    0.06
     Bs
    0.06
    Activations Density 0.008%

    No Known Activations