© 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. 120628
    Prev
    Next
    INDEX
    Explanations

    main/resources/ or src/test/resources/

    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
     жела
    -0.06
     encabez
    -0.06
     deseja
    -0.06
    ,
    -0.06
     کمک
    -0.06
     Tiểu
    -0.06
    దాయ
    -0.06
    iet
    -0.06
     manifestation
    -0.06
    ıy
    -0.05
    POSITIVE LOGITS
    業界
    0.06
    行业的
    0.06
    }}+
    0.06
    
    0.06
    acamole
    0.06
     Criteria
    0.06
     ছুই
    0.06
    瘟
    0.05
    业界
    0.05
     costs
    0.05
    Activations Density 0.001%

    No Known Activations