© 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. 117120
    Prev
    Next
    INDEX
    Explanations

    "not only X but also" construction

    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
     толькі
    -0.06
    無い
    -0.06
    ONLY
    -0.06
     هذا
    -0.06
    ี้ยว
    -0.06
     fuese
    -0.06
     này
    -0.06
    ема
    -0.06
     not
    -0.06
     non
    -0.06
    POSITIVE LOGITS
     combines
    0.08
     combining
    0.07
     শু
    0.06
    قبل
    0.06
     適
    0.06
    適
    0.06
     conveys
    0.06
     σε
    0.06
    before
    0.06
     are
    0.06
    Activations Density 0.008%

    No Known Activations