© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6944
    Prev
    Next
    INDEX
    Explanations

    transactional exception imports

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

    The neuron fires strongly on Java import/package declarations—i.e. fully qualified package names in import statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    込ま
    -0.88
    UserController
    -0.85
     hòa
    -0.82
    HSA
    -0.81
     路
    -0.79
    টি
    -0.79
    Tolerance
    -0.79
    EVERY
    -0.78
    career
    -0.77
    literally
    -0.77
    POSITIVE LOGITS
     found
    0.90
     transactional
    0.86
     Sort
    0.86
     transaction
    0.86
     Exceptions
    0.85
     exceptions
    0.83
    例外
    0.82
    qrstuvwxyz
    0.82
    exceptions
    0.80
     exception
    0.80
    Activations Density 0.007%

    No Known Activations