© 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. 128817
    Prev
    Next
    INDEX
    Explanations

    to other

    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
    分别
    -0.07
     ketiga
    -0.06
     각각
    -0.06
    ../../../
    -0.06
     respective
    -0.06
     तीनों
    -0.06
    These
    -0.06
     শহীদ
    -0.06
     respectively
    -0.06
    それぞれ
    -0.06
    POSITIVE LOGITS
    ন্যা
    0.06
     جبکہ
    0.06
    似的
    0.06
    si
    0.06
     at
    0.05
    ْع
    0.05
     for
    0.05
    ходження
    0.05
     Byzantine
    0.05
    worker
    0.05
    Activations Density 0.080%

    No Known Activations