© 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. 116482
    Prev
    Next
    INDEX
    Explanations

    assert checking boolean conditions

    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
    組み合わせ
    -0.07
     zonder
    -0.07
    Further
    -0.06
    あす楽
    -0.06
     fără
    -0.06
     kasnije
    -0.06
     proves
    -0.06
     without
    -0.06
     пя
    -0.06
     tanpa
    -0.06
    POSITIVE LOGITS
     not
    0.08
     to
    0.07
     ليس
    0.06
     όχι
    0.06
    不是
    0.06
     কারাগ
    0.06
     supaya
    0.06
     bukan
    0.06
     NOT
    0.06
     для
    0.06
    Activations Density 0.002%

    No Known Activations