© 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. 116306
    Prev
    Next
    INDEX
    Explanations

    programming syntax or code snippets

    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
     Correspond
    -0.07
     соответствующие
    -0.07
     stimmt
    -0.07
    Amid
    -0.06
     corresponds
    -0.06
    appropriate
    -0.06
     enclosed
    -0.06
     соответству
    -0.06
    운데
    -0.06
     соответствующих
    -0.06
    POSITIVE LOGITS
     poorer
    0.08
    traj
    0.06
     poorest
    0.06
     poor
    0.06
     직원
    0.05
     দেয়নি
    0.05
    ومین
    0.05
     Nacional
    0.05
     পৃথিবীর
    0.05
     সম্পূর্ণরূপে
    0.05
    Activations Density 0.003%

    No Known Activations