© 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. 118354
    Prev
    Next
    INDEX
    Explanations

    Kubernetes metadata or localization context

    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
     دینا
    -0.06
    ;
    -0.06
     vence
    -0.06
     responde
    -0.06
    ชนะ
    -0.06
    ；
    -0.06
     variables
    -0.05
    这是一个
    -0.05
     effects
    -0.05
     kako
    -0.05
    POSITIVE LOGITS
    prepare
    0.06
    uparavant
    0.06
     now
    0.06
     jetzt
    0.06
    atai
    0.06
    平时
    0.06
     impover
    0.06
    今まで
    0.06
    Hopefully
    0.06
     milhares
    0.06
    Activations Density 0.002%

    No Known Activations