© 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. 22-GEMMASCOPE-RES-131K
    7. 79779
    Prev
    Next
    INDEX
    Explanations

    acute and, perceptions of, Ashburn, Dena

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

    The neuron activates on code import or include directives (e.g. “using …;” or top‐level 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_22/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
    ми
    -0.86
     svoj
    -0.84
     жы
    -0.84
    4
    -0.81
     новые
    -0.80
    的世界
    -0.80
    ст
    -0.79
    ви
    -0.78
     uporab
    -0.78
    л
    -0.77
    POSITIVE LOGITS
     kokos
    1.02
     genoux
    1.02
     zodia
    0.95
    鲥
    0.95
     ministra
    0.94
     ralla
    0.93
     igre
    0.92
     perles
    0.92
     diing
    0.91
    Dura
    0.90
    Activations Density 0.002%

    No Known Activations