© 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. 130559
    Prev
    Next
    INDEX
    Explanations

    comparison between groups

    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
     definite
    -0.06
     أع
    -0.06
    tle
    -0.06
     mientras
    -0.06
     scarce
    -0.06
     whereas
    -0.06
     enquanto
    -0.06
    くちゃ
    -0.06
     acquisition
    -0.06
    重要的
    -0.06
    POSITIVE LOGITS
     methodology
    0.06
    スタンダード
    0.06
     टीमों
    0.06
     induced
    0.06
    受到了
    0.06
     杨
    0.06
     metodologia
    0.06
    ፊት
    0.05
     sistemi
    0.05
     podrá
    0.05
    Activations Density 0.045%

    No Known Activations