© 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. 129358
    Prev
    Next
    INDEX
    Explanations

    instantiating program components

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

    The neuron fires on occurrences of the word “create” (e.g. method or constructor calls named create).

    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
     .......
    -1.99
     !!!!
    -1.81
    揸
    -1.79
    揾
    -1.78
    ︲
    -1.77
     predominantly
    -1.76
     !!!!!
    -1.73
    
    -1.73
     Dinas
    -1.70
    睜
    -1.70
    POSITIVE LOGITS
    Maybe
    1.98
     for
    1.91
     Maybe
    1.88
    Perhaps
    1.76
    Several
    1.73
     These
    1.70
    Shortly
    1.69
    Some
    1.67
     as
    1.66
    Putting
    1.64
    Activations Density 0.009%

    No Known Activations