© 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. 128574
    Prev
    Next
    INDEX
    Explanations

    not only, instead of, rather than

    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
    ഒരു
    -0.06
    कोई
    -0.06
    संयुक्त
    -0.06
     பகிர்ந்து
    -0.06
    ásticos
    -0.06
     പിന്തുണ
    -0.06
     چک
    -0.06
     preached
    -0.06
    dairy
    -0.05
    வார
    -0.05
    POSITIVE LOGITS
     nejen
    0.10
    だけでなく
    0.10
     both
    0.09
     både
    0.08
    both
    0.08
    不但
    0.08
     όχι
    0.08
     not
    0.08
    不仅
    0.08
    不僅
    0.08
    Activations Density 0.010%

    No Known Activations