© 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. 127967
    Prev
    Next
    INDEX
    Explanations

    in vitro, Achilles, Transmission, LeChee

    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
    "./
    -0.06
    クー
    -0.06
     contagion
    -0.06
     skala
    -0.06
     standards
    -0.06
     স্ট্যান্ডার্ড
    -0.06
    appropri
    -0.06
     appropriately
    -0.05
     sampled
    -0.05
    を出
    -0.05
    POSITIVE LOGITS
    专利
    0.06
    不过
    0.06
     Gentle
    0.06
     Mazda
    0.06
     Dental
    0.06
    追求
    0.06
     Беларусі
    0.06
    不過
    0.06
     bevorzug
    0.06
     prophecies
    0.06
    Activations Density 0.013%

    No Known Activations