© 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. 130107
    Prev
    Next
    INDEX
    Explanations

    lists of items joined by "and"

    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
     like
    -0.06
     nawet
    -0.06
     even
    -0.05
    回避
    -0.05
     হোক
    -0.05
     habitual
    -0.05
     rép
    -0.05
    埼
    -0.05
     ảnh
    -0.05
    वि
    -0.05
    POSITIVE LOGITS
    если
    0.07
    makefile
    0.07
    めっちゃ
    0.07
    精心
    0.07
     имеется
    0.06
     brings
    0.06
    😸
    0.06
     陈
    0.06
    📽
    0.06
     circa
    0.06
    Activations Density 0.021%

    No Known Activations