© 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. 116326
    Prev
    Next
    INDEX
    Explanations

    we or our followed by a noun or verb

    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
    /(
    -0.07
     тебя
    -0.06
     you
    -0.06
     тобі
    -0.06
     discutir
    -0.06
    在你
    -0.06
     члена
    -0.06
    让你
    -0.06
    You
    -0.06
    していた
    -0.06
    POSITIVE LOGITS
     are
    0.07
     attempts
    0.07
    自己
    0.07
     angrily
    0.07
     becomes
    0.07
     can
    0.07
     resembles
    0.07
     boasts
    0.06
     ແມ່ນ
    0.06
    由于
    0.06
    Activations Density 0.025%

    No Known Activations