© 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. 117424
    Prev
    Next
    INDEX
    Explanations

    United States Court of Appeals

    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
     фактически
    -0.06
     duidelijk
    -0.06
    교
    -0.06
    administrative
    -0.06
     majority
    -0.06
     एजु
    -0.06
     मैनु
    -0.06
     administrative
    -0.06
     αρκε
    -0.06
    薀
    -0.06
    POSITIVE LOGITS
    ដល់
    0.06
    FileWriter
    0.06
    getLast
    0.06
     صفح
    0.06
     सुष
    0.06
     detectives
    0.06
     ফৌজ
    0.05
    Closeup
    0.05
    bdm
    0.05
     Dienste
    0.05
    Activations Density 0.006%

    No Known Activations