© 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. 120495
    Prev
    Next
    INDEX
    Explanations

    code blocks ending sentences

    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
     comme
    -0.07
     succeeds
    -0.07
     como
    -0.07
     accomplishes
    -0.07
     अलग
    -0.06
     undergraduate
    -0.06
     riêng
    -0.06
     가장
    -0.06
     occasionally
    -0.06
     suy
    -0.06
    POSITIVE LOGITS
    避免
    0.06
    减少
    0.06
     করাই
    0.06
    下载
    0.06
    publication
    0.06
    defence
    0.06
     harsher
    0.06
     Maui
    0.06
     healthier
    0.06
     Prevent
    0.06
    Activations Density 0.001%

    No Known Activations