© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128802
    Prev
    Next
    INDEX
    Explanations

    bag and keychain descriptions

    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
     аллер
    -0.06
     각각
    -0.06
     गोद
    -0.06
     commemorating
    -0.06
     embod
    -0.06
     ઉત્પાદ
    -0.06
    ysz
    -0.06
    樣子
    -0.06
     truyền
    -0.06
     vielen
    -0.06
    POSITIVE LOGITS
     data
    0.06
    banking
    0.06
     banking
    0.06
    ⁶
    0.06
    的数据
    0.06
     monitor
    0.06
    িলারা
    0.06
     長財布
    0.06
     CC
    0.06
     खोले
    0.05
    Activations Density 0.023%

    No Known Activations