© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128029
    Prev
    Next
    INDEX
    Explanations

    insurance types

    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
    Negative Logits
     tärke
    -0.06
     любого
    -0.06
     bring
    -0.06
    Totally
    -0.06
     leave
    -0.06
     какого
    -0.06
     be
    -0.05
     irrelevant
    -0.05
     obscure
    -0.05
     нашего
    -0.05
    POSITIVE LOGITS
     honoring
    0.06
    高
    0.06
    的方式
    0.06
     dị
    0.06
    τικών
    0.06
    azia
    0.06
     antitrust
    0.06
    nicht
    0.06
     Nicht
    0.05
    only
    0.05
    Activations Density 0.002%

    No Known Activations