© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130690
    Prev
    Next
    INDEX
    Explanations

    family relationships (son, daughter, father, sister, husband, couple, baby)

    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
     когда
    -0.07
     Quando
    -0.07
     glamorous
    -0.07
     when
    -0.06
     Когда
    -0.06
     When
    -0.06
     cuando
    -0.06
     повышен
    -0.06
     quando
    -0.06
     Currently
    -0.06
    POSITIVE LOGITS
     tandis
    0.07
    整个
    0.06
     qubit
    0.06
    據
    0.06
     nieco
    0.06
    据
    0.06
    整個
    0.06
     quelques
    0.06
    их
    0.06
    加以
    0.06
    Activations Density 0.014%

    No Known Activations