© 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. 130440
    Prev
    Next
    INDEX
    Explanations

    smiling or laughing

    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
     regarding
    -0.06
     storage
    -0.06
     bitcoin
    -0.06
    员
    -0.06
     jQuery
    -0.06
    אל
    -0.06
     дэ
    -0.06
     xbox
    -0.06
     Ow
    -0.06
     cex
    -0.06
    POSITIVE LOGITS
    yes
    0.06
     सर्वाधिक
    0.06
    Yes
    0.06
     merah
    0.06
     Tok
    0.06
     Nếu
    0.06
     yes
    0.06
     Yes
    0.06
    Tok
    0.06
     기타
    0.06
    Activations Density 0.001%

    No Known Activations