© 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. 130016
    Prev
    Next
    INDEX
    Explanations

    configuration and system settings

    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
    读取
    -0.06
     each
    -0.06
    :
    -0.06
     আলাদা
    -0.06
     प्रकाश
    -0.06
    person
    -0.06
    Aaj
    -0.06
    会在
    -0.05
    AllResult
    -0.05
    ্ঠ
    -0.05
    POSITIVE LOGITS
     حين
    0.08
    ใน
    0.06
     in
    0.06
     tercera
    0.06
     Reducing
    0.06
     lesser
    0.06
    に
    0.06
    無
    0.06
    খালী
    0.06
     когато
    0.06
    Activations Density 0.001%

    No Known Activations