© 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. 130315
    Prev
    Next
    INDEX
    Explanations

    is/are followed by descriptive words

    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
     بواسطة
    -0.08
     using
    -0.07
    бовать
    -0.06
     যেহেতু
    -0.06
     sommige
    -0.06
     (
    -0.06
     proudly
    -0.06
    example
    -0.06
     by
    -0.06
     plenty
    -0.06
    POSITIVE LOGITS
    是为了
    0.07
    是要
    0.06
     necesaria
    0.06
    ور
    0.06
     necessari
    0.06
    必要的
    0.06
    乃至
    0.06
    จริง
    0.06
    的确
    0.06
    本来
    0.06
    Activations Density 0.026%

    No Known Activations