© 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. 130468
    Prev
    Next
    INDEX
    Explanations

    Magento licensing information

    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
     매우
    -0.06
     with
    -0.06
     ricco
    -0.06
     
    -0.06
     দারুণ
    -0.06
    %@",
    -0.06
     หลังจาก
    -0.05
     cannot
    -0.05
     gehört
    -0.05
     you
    -0.05
    POSITIVE LOGITS
     probabilmente
    0.07
     cosidd
    0.06
     też
    0.06
     disseminating
    0.06
     Neighbourhood
    0.06
     socalled
    0.06
    ้ํา
    0.06
    লালের
    0.06
     ſ
    0.06
    荘
    0.06
    Activations Density 0.002%

    No Known Activations