© 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. 117910
    Prev
    Next
    INDEX
    Explanations

    closures and shutdowns

    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
     special
    -0.06
    📥
    -0.06
     специа
    -0.06
    去年
    -0.06
     current
    -0.06
    创建
    -0.05
     времени
    -0.05
    に対応
    -0.05
    special
    -0.05
     উন্নয়নের
    -0.05
    POSITIVE LOGITS
     대부분
    0.09
     niektó
    0.08
     plupart
    0.08
    ほとんど
    0.07
     большинстве
    0.07
     relâche
    0.07
     algunos
    0.07
     функції
    0.07
     sommige
    0.07
     větš
    0.07
    Activations Density 0.017%

    No Known Activations