© 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. 115974
    Prev
    Next
    INDEX
    Explanations

    separately work

    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
     chỉ
    -0.07
     only
    -0.07
     replied
    -0.06
     fusc
    -0.06
     اذا
    -0.06
    something
    -0.06
    걔
    -0.06
    ">:
    -0.06
     路
    -0.06
    使用了
    -0.06
    POSITIVE LOGITS
    separate
    0.08
     separate
    0.08
    separ
    0.07
     associated
    0.07
    ాతీయ
    0.07
     jednocześnie
    0.07
    Separate
    0.07
     separately
    0.07
    同時に
    0.06
     simultaneously
    0.06
    Activations Density 0.007%

    No Known Activations