© 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. 128955
    Prev
    Next
    INDEX
    Explanations

    our, our, our, our, our, our, our, our, our, our

    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
     olika
    -0.07
     일단
    -0.07
     '~
    -0.07
     variously
    -0.06
     différents
    -0.06
     différentes
    -0.06
     varsa
    -0.06
     اولا
    -0.06
    デ
    -0.06
    ชาว
    -0.06
    POSITIVE LOGITS
     our
    0.10
    私たちの
    0.08
     enthusiasts
    0.07
    私たち
    0.07
     ہماری
    0.07
    amız
    0.07
    fundamental
    0.07
     আমাদের
    0.06
    当我们
    0.06
     arguably
    0.06
    Activations Density 0.089%

    No Known Activations