© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101220
    Prev
    Next
    INDEX
    Explanations

    emergencies or failures

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

    The neuron is essentially keyed to the legal/conditional phrase “in the event of.”

    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
     \%
    -2.03
     \'
    -2.02
     celebrates
    -1.87
    锲
    -1.85
    」
    -1.81
     \#
    -1.80
     TÉCNICA
    -1.78
     chances
    -1.78
    jaciół
    -1.73
     reconnaît
    -1.73
    POSITIVE LOGITS
    蜮
    1.94
    b
    1.90
     These
    1.88
    f
    1.82
    li
    1.81
     Moreover
    1.78
    なので
    1.73
    m
    1.70
    囖
    1.69
     Furthermore
    1.68
    Activations Density 0.002%

    No Known Activations