© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116981
    Prev
    Next
    INDEX
    Explanations

    Los Angeles, Daniel Radcliffe, pregnancy

    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
     verific
    -0.06
     verified
    -0.06
     interim
    -0.06
     протягом
    -0.06
     أكتوبر
    -0.05
     Ranking
    -0.05
     newly
    -0.05
     تاريخ
    -0.05
    insertion
    -0.05
     descre
    -0.05
    POSITIVE LOGITS
    更大的
    0.07
     vhod
    0.07
    本当に
    0.07
     بیشتری
    0.07
    更好的
    0.06
    如此
    0.06
    hoz
    0.06
     sadece
    0.06
    更大
    0.06
     শুধু
    0.06
    Activations Density 0.002%

    No Known Activations