© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130903
    Prev
    Next
    INDEX
    Explanations

    other/details/about/next

    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
     this
    -0.06
    går
    -0.06
    onet
    -0.05
     twelve
    -0.05
     not
    -0.05
     fifty
    -0.05
    婕
    -0.05
     takt
    -0.05
     fifteen
    -0.05
    สัมพันธ์
    -0.05
    POSITIVE LOGITS
    其他
    0.07
     kojoj
    0.07
     other
    0.06
     વસ્તુ
    0.06
     особенностей
    0.06
    アイテム
    0.06
     когато
    0.06
    その他
    0.06
     который
    0.06
     обновления
    0.06
    Activations Density 0.001%

    No Known Activations