© 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. 129279
    Prev
    Next
    INDEX
    Explanations

    document submission status

    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
     unavoidable
    -0.07
     नेत्र
    -0.07
     Einkauf
    -0.06
     não
    -0.06
    添加
    -0.06
     Validation
    -0.06
    验证
    -0.06
    已
    -0.06
    關鍵
    -0.06
     remaining
    -0.06
    POSITIVE LOGITS
     প্রভৃতি
    0.06
     جول
    0.06
    Her
    0.06
     proliferating
    0.06
     করেছেন
    0.05
    Every
    0.05
    мену
    0.05
    рили
    0.05
    ナビ
    0.05
    Any
    0.05
    Activations Density 0.001%

    No Known Activations