© 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. 117254
    Prev
    Next
    INDEX
    Explanations

    and causing, consent, financial

    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
     की
    -0.07
     något
    -0.06
     wraz
    -0.06
     із
    -0.06
     ಹಾಗೂ
    -0.06
     questa
    -0.06
     défis
    -0.06
     as
    -0.06
     практически
    -0.06
    Projects
    -0.06
    POSITIVE LOGITS
    galkan
    0.07
    ือก
    0.06
    etty
    0.06
     equivalents
    0.06
    :
    0.06
     repeal
    0.06
     zlo
    0.05
    uins
    0.05
     four
    0.05
     olan
    0.05
    Activations Density 0.006%

    No Known Activations