© 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. 115968
    Prev
    Next
    INDEX
    Explanations

    located at

    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
    只有
    -0.08
     only
    -0.07
    这张
    -0.07
     also
    -0.07
     также
    -0.07
    这两个
    -0.07
     genießen
    -0.07
    実際の
    -0.07
    进口
    -0.07
     ასევე
    -0.07
    POSITIVE LOGITS
    But
    0.06
     But
    0.06
     Friedman
    0.05
     Rebecca
    0.05
    स्तर
    0.05
    ”
    0.05
    —
    0.05
     Lee
    0.05
     জড়িয়ে
    0.05
     ],
    0.05
    Activations Density 0.006%

    No Known Activations