© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119300
    Prev
    Next
    INDEX
    Explanations

    legal decisions and dates

    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
     never
    -0.07
    lovak
    -0.06
     tapis
    -0.06
     begin
    -0.06
     passes
    -0.06
     affectionately
    -0.06
     единственный
    -0.06
     રચ
    -0.06
    passes
    -0.06
     ወይም
    -0.05
    POSITIVE LOGITS
    你
    0.06
    数据
    0.06
    主管部门
    0.06
     색
    0.06
    ◯
    0.05
     为
    0.05
     你
    0.05
     มา
    0.05
    因为
    0.05
     injurious
    0.05
    Activations Density 0.001%

    No Known Activations