© 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. 116536
    Prev
    Next
    INDEX
    Explanations

    marriage or refusal

    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
    這裡是
    -0.07
     svom
    -0.07
    巔
    -0.06
    ここは
    -0.06
     waterfowl
    -0.06
     aree
    -0.06
     skupiny
    -0.06
     zonas
    -0.06
     zone
    -0.06
    former
    -0.06
    POSITIVE LOGITS
     marry
    0.07
     Mädchen
    0.07
     gerçekleş
    0.07
     vetting
    0.07
     marrying
    0.07
    娶
    0.06
    ができ
    0.06
     alliances
    0.06
     announcement
    0.06
    áus
    0.06
    Activations Density 0.003%

    No Known Activations