© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70673
    Prev
    Next
    INDEX
    Explanations

    checking assertions and test results

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on uses of test assertion calls (e.g. “assert”, “Assert.assert…”, “BOOST_CHECK”, etc.) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    -2.45
    ]
    -2.14
     Again
    -2.06
    4
    -1.94
    9
    -1.85
    6
    -1.85
    3
    -1.85
     Notably
    -1.81
     Both
    -1.79
     Previously
    -1.79
    POSITIVE LOGITS
    砹
    1.59
     jestli
    1.58
     かわいい
    1.55
    僦
    1.52
    昞
    1.49
    綃
    1.45
    苼
    1.42
    thisis
    1.41
    ordat
    1.41
    ता
    1.41
    Activations Density 0.001%

    No Known Activations