© 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. 117882
    Prev
    Next
    INDEX
    Explanations

    plaintiff versus defendant

    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
     a
    -0.06
     and
    -0.06
     determine
    -0.06
     и
    -0.06
     of
    -0.06
    確定
    -0.06
     учитель
    -0.06
    誰
    -0.06
     abhäng
    -0.06
    មុ
    -0.06
    POSITIVE LOGITS
     moist
    0.07
    Mono
    0.06
     многочис
    0.06
    ..
    0.06
    킁
    0.06
    Debugging
    0.05
    Frank
    0.05
    ائن
    0.05
    ccn
    0.05
     चांद
    0.05
    Activations Density 0.003%

    No Known Activations