© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131007
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
     після
    -0.07
     Размер
    -0.06
     поверх
    -0.06
     nakon
    -0.06
     NM
    -0.06
    𝚈
    -0.06
     Украи
    -0.06
     แต่
    -0.06
     tamanho
    -0.06
    完成后
    -0.06
    POSITIVE LOGITS
     the
    0.07
    cyte
    0.07
     doppia
    0.06
    Ve
    0.06
     might
    0.06
     উচিৎ
    0.06
     दूस
    0.06
     multiple
    0.05
     because
    0.05
     that
    0.05
    Activations Density 0.001%

    No Known Activations