© 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. 116762
    Prev
    Next
    INDEX
    Explanations

    seasonal annually springtime

    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
     now
    -0.08
     jetzt
    -0.06
     teraz
    -0.06
     теперь
    -0.06
     ahora
    -0.06
     on
    -0.06
     architect
    -0.06
     NOW
    -0.06
    海底
    -0.06
     тепер
    -0.06
    POSITIVE LOGITS
    еха
    0.06
    每年
    0.06
     популя
    0.06
     seasonal
    0.06
    derived
    0.06
     annually
    0.06
     southbound
    0.06
     springtime
    0.06
     mỗi
    0.06
    这条
    0.06
    Activations Density 0.007%

    No Known Activations