© 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. 128569
    Prev
    Next
    INDEX
    Explanations

    hazardous environments and conditions

    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
     multicolor
    -0.07
     apoio
    -0.06
     HQ
    -0.06
     Lounge
    -0.06
     inevitable
    -0.06
     comercial
    -0.06
     penjualan
    -0.06
    Our
    -0.06
    ويل
    -0.06
     اکثریت
    -0.06
    POSITIVE LOGITS
     hazardous
    0.07
     environment
    0.06
     υπηρε
    0.06
     محیط
    0.06
     никаких
    0.06
     Hazardous
    0.06
    environment
    0.05
    的环境
    0.05
     environmental
    0.05
    环境
    0.05
    Activations Density 0.028%

    No Known Activations