© 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. 129999
    Prev
    Next
    INDEX
    Explanations

    global contract deal

    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
     balconies
    -0.07
     okresie
    -0.07
     ಬಾರಿ
    -0.06
     యొక్క
    -0.06
     রজ
    -0.06
     மாற்றம்
    -0.06
     sayang
    -0.06
     пър
    -0.06
    比如
    -0.06
    فيق
    -0.06
    POSITIVE LOGITS
     criminal
    0.07
     चाहिये
    0.06
     Criminal
    0.06
    刑
    0.06
    сред
    0.06
    彻底
    0.06
     мировой
    0.05
     centralized
    0.05
     talent
    0.05
     gigantic
    0.05
    Activations Density 0.005%

    No Known Activations