© 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. 118621
    Prev
    Next
    INDEX
    Explanations

    court case citations and appeals

    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
     ocupa
    -0.07
     viven
    -0.07
     één
    -0.06
     гара
    -0.06
     restricts
    -0.06
     одну
    -0.06
     fluctuates
    -0.06
     自己
    -0.06
     får
    -0.06
    কিং
    -0.06
    POSITIVE LOGITS
    ssystem
    0.06
     biraz
    0.06
    6
    0.06
     Aussage
    0.06
    niejszych
    0.05
    =
    0.05
    처럼
    0.05
     malgré
    0.05
     agak
    0.05
     थोड़ा
    0.05
    Activations Density 0.015%

    No Known Activations