© 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. 118433
    Prev
    Next
    INDEX
    Explanations

    concerns and ethical considerations

    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
     никаких
    -0.06
    定
    -0.06
     "
    -0.06
    ဖြေ
    -0.06
    हमने
    -0.06
    我们会
    -0.06
     data
    -0.06
    copy
    -0.05
     बाजार
    -0.05
    olu
    -0.05
    POSITIVE LOGITS
    鼓勵
    0.08
     stunning
    0.07
    整體
    0.07
     splendor
    0.07
    影響
    0.07
     splendour
    0.07
     splendid
    0.07
    勧め
    0.07
     تاثیر
    0.07
     achievable
    0.07
    Activations Density 0.002%

    No Known Activations