© 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. 130371
    Prev
    Next
    INDEX
    Explanations

    settlements and localities

    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
    过去的
    -0.06
    難しい
    -0.06
    困難
    -0.06
     unavailability
    -0.06
    当時
    -0.06
    鑰
    -0.06
    Difficult
    -0.06
    extremely
    -0.06
     янва
    -0.06
     имели
    -0.06
    POSITIVE LOGITS
     connects
    0.06
     consists
    0.06
     operates
    0.06
     defines
    0.06
     includes
    0.06
    washed
    0.06
     Hoe
    0.06
     involves
    0.06
     engages
    0.05
     நகை
    0.05
    Activations Density 0.022%

    No Known Activations