© 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. 130241
    Prev
    Next
    INDEX
    Explanations

    depends on factors

    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
    యితే
    -0.07
     ጭ
    -0.06
    দারি
    -0.06
     epidemi
    -0.06
     contribuir
    -0.06
    äude
    -0.06
     कुसुम
    -0.06
     быть
    -0.06
    THIS
    -0.06
    更能
    -0.06
    POSITIVE LOGITS
     first
    0.07
     પહેલા
    0.07
    :
    0.06
     স্বভাব
    0.06
     blem
    0.06
     впервые
    0.06
    第一次
    0.06
     maintenance
    0.06
     восста
    0.05
    ாய்ச்சி
    0.05
    Activations Density 0.008%

    No Known Activations