© 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. 118659
    Prev
    Next
    INDEX
    Explanations

    psychological and work 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
     großer
    -0.07
     informativa
    -0.06
     informativo
    -0.06
     preventiva
    -0.06
     présentation
    -0.06
     einiger
    -0.06
    ບໍ
    -0.06
     prevention
    -0.06
     mooi
    -0.06
     alarma
    -0.06
    POSITIVE LOGITS
     one
    0.06
    which
    0.06
     সহজেই
    0.06
     کھلا
    0.06
    જે
    0.06
     luggage
    0.06
    具有
    0.06
     স্পষ্ট
    0.06
     одну
    0.06
     dezelfde
    0.05
    Activations Density 0.020%

    No Known Activations