© 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. 118490
    Prev
    Next
    INDEX
    Explanations

    Jewish people and Israel

    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
     disfraz
    -0.06
    ごとに
    -0.06
     increasingly
    -0.06
     cotidian
    -0.06
    像是
    -0.06
     konusu
    -0.06
    getClass
    -0.05
    め
    -0.05
     yine
    -0.05
    受到
    -0.05
    POSITIVE LOGITS
     оригина
    0.07
     sostenibilidad
    0.07
     uniquement
    0.06
    目标的
    0.06
     জায়গা
    0.06
     bertujuan
    0.06
     বজায়
    0.06
    anskje
    0.06
     જગ્યા
    0.06
     solely
    0.06
    Activations Density 0.002%

    No Known Activations