© 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. 105046
    Prev
    Next
    INDEX
    Explanations

    instantiate objects

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

    the word "instantiate" and its variations in programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on words related to instantiating objects (e.g. “instantiate,” “instantiating,” etc.).

    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
    薷
    -2.13
     are
    -2.06
     dopo
    -1.99
     lorsqu
    -1.98
    
    -1.97
    人的
    -1.95
    ine
    -1.94
     )
    -1.93
    鹋
    -1.89
     praktische
    -1.88
    POSITIVE LOGITS
     a
    2.25
    ]
    2.23
     an
    1.95
    {
    1.87
     متحده
    1.86
    Other
    1.82
     intensely
    1.81
     rudimentary
    1.80
     unequivocally
    1.77
     substantial
    1.76
    Activations Density 0.005%

    No Known Activations