© 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. 117161
    Prev
    Next
    INDEX
    Explanations

    code keywords and programming constructs

    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
    对应的
    -0.08
     corresponding
    -0.07
     असलेला
    -0.07
     offsetting
    -0.06
     originally
    -0.06
     scripted
    -0.06
     असलेली
    -0.06
     ব্যাট
    -0.06
    corresponding
    -0.06
     соответству
    -0.06
    POSITIVE LOGITS
     NOTE
    0.07
     ONLY
    0.06
     NEVER
    0.06
     please
    0.06
     ALWAYS
    0.06
     왼쪽
    0.06
    Please
    0.06
     🤗
    0.06
     Array
    0.06
     !!
    0.06
    Activations Density 0.001%

    No Known Activations