© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119270
    Prev
    Next
    INDEX
    Explanations

    affinity purification chromatography

    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
    Not in Any Lists

    No Comments

    Negative Logits
     apparently
    -0.06
     بعد
    -0.06
     അള
    -0.06
     после
    -0.06
     pärast
    -0.06
     নির্ধারণ
    -0.06
    后
    -0.06
     dupa
    -0.06
     after
    -0.06
     Apparently
    -0.06
    POSITIVE LOGITS
     comprises
    0.07
     comprising
    0.06
     umfasst
    0.06
     deixou
    0.06
    antically
    0.06
     conosce
    0.06
     listOf
    0.06
    other
    0.06
     соб
    0.06
     CLOS
    0.06
    Activations Density 0.014%

    No Known Activations