© 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. 118120
    Prev
    Next
    INDEX
    Explanations

    receiving communications and confirmations

    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
    รา
    -0.06
     शिष्य
    -0.06
     ምክንያት
    -0.06
    要求
    -0.06
    选择
    -0.06
     ショルダーバッグ
    -0.06
     katıl
    -0.06
    حن
    -0.06
     mensagem
    -0.06
     encontraron
    -0.06
    POSITIVE LOGITS
    новь
    0.07
     Usually
    0.07
     whereupon
    0.06
    Usually
    0.06
     vanligt
    0.06
     caching
    0.06
     usually
    0.06
    usually
    0.06
    нову
    0.06
     along
    0.06
    Activations Density 0.003%

    No Known Activations