© 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. 116021
    Prev
    Next
    INDEX
    Explanations

    upon request or otherwise indicated

    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
     снова
    -0.07
     вновь
    -0.07
     erneut
    -0.07
    λευτα
    -0.07
     новая
    -0.07
    再び
    -0.06
     remaining
    -0.06
    之後
    -0.06
     później
    -0.06
     superiority
    -0.06
    POSITIVE LOGITS
    :
    0.06
     нашу
    0.06
     negotiate
    0.06
     redo
    0.06
     write
    0.05
    書き
    0.05
     اجازه
    0.05
    惠
    0.05
     your
    0.05
     I
    0.05
    Activations Density 0.003%

    No Known Activations