© 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. 118736
    Prev
    Next
    INDEX
    Explanations

    health insurance and medical plans

    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
    買い物
    -0.07
    બાદ
    -0.07
     jusqu
    -0.06
    衝撃
    -0.06
     جذ
    -0.06
    busca
    -0.06
    将于
    -0.06
     پس
    -0.06
    最後まで
    -0.06
     nasceu
    -0.06
    POSITIVE LOGITS
     गोपनीयता
    0.06
    Valentine
    0.06
     Minerva
    0.06
     എത്ര
    0.06
     in
    0.06
     ister
    0.06
     এনে
    0.06
    ებში
    0.06
     دب
    0.05
     hunch
    0.05
    Activations Density 0.010%

    No Known Activations