© 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. 102109
    Prev
    Next
    INDEX
    Explanations

    cognitive control and interventions

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

    The neuron is selectively activating on the standalone uppercase token “AS.”

    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
    .
    -1.79
    随之
    -1.75
     Eventually
    -1.63
    Then
    -1.59
    紧接着
    -1.54
    歺
    -1.53
    Actually
    -1.50
     Thus
    -1.49
    Therefore
    -1.48
     rękaw
    -1.48
    POSITIVE LOGITS
     entiendo
    2.11
     motivadoras
    1.86
     detalladas
    1.79
     parfü
    1.78
     adecuadas
    1.74
     that
    1.68
     quería
    1.62
     土産
    1.59
     milyon
    1.59
    AISSEE
    1.56
    Activations Density 0.077%

    No Known Activations