© 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. 118632
    Prev
    Next
    INDEX
    Explanations

    code imports

    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
     kopp
    -0.06
     begge
    -0.06
    нная
    -0.06
    ಂತಹ
    -0.06
    لە
    -0.06
     aggregate
    -0.06
     cả
    -0.06
    jö
    -0.06
    足够的
    -0.06
    лює
    -0.06
    POSITIVE LOGITS
     sem
    0.06
     صدای
    0.06
     информации
    0.06
    HttpClient
    0.06
    やす
    0.05
    信息的
    0.05
    ʻ
    0.05
     tampilan
    0.05
     তথ্য
    0.05
    apiKey
    0.05
    Activations Density 0.023%

    No Known Activations