© 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. 117690
    Prev
    Next
    INDEX
    Explanations

    technical terms and abbreviations

    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
    several
    -0.06
     riconoscimento
    -0.06
     several
    -0.06
     getView
    -0.06
     అనేక
    -0.06
     നിരവധി
    -0.06
     सुमारे
    -0.06
     számos
    -0.06
     sejumlah
    -0.06
    err
    -0.06
    POSITIVE LOGITS
     těch
    0.06
     Quebec
    0.06
    欲しい
    0.06
    leding
    0.06
     new
    0.06
     নতুন
    0.06
    िस
    0.05
    Philippines
    0.05
     unemployment
    0.05
    前面的
    0.05
    Activations Density 0.003%

    No Known Activations