© 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. 120056
    Prev
    Next
    INDEX
    Explanations

    Conditional verb constructions

    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
    ときに
    -0.06
     lorsqu
    -0.06
    eBay
    -0.06
    時に
    -0.06
     når
    -0.06
     från
    -0.06
     నుండి
    -0.06
     وقتی
    -0.06
    during
    -0.06
     सप
    -0.06
    POSITIVE LOGITS
     нашей
    0.08
     slower
    0.08
     our
    0.07
     наших
    0.07
     naszej
    0.07
     undoubtedly
    0.07
     हमने
    0.07
     meie
    0.06
    ไม่มี
    0.06
     naszym
    0.06
    Activations Density 0.010%

    No Known Activations