© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118948
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by forms of 'do'

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    findOne
    -0.89
     Act
    -0.89
    不大
    -0.83
    ův
    -0.81
    lasia
    -0.80
    بررسی
    -0.77
    可不是
    -0.77
    greSQL
    -0.76
    mainAxisSize
    -0.75
     włas
    -0.75
    POSITIVE LOGITS
     do
    2.31
    do
    1.61
     doing
    1.39
     does
    1.37
    Do
    1.30
     Do
    1.20
    does
    1.15
    做什么
    1.15
    doing
    1.12
    Does
    1.07
    Activations Density 0.024%

    No Known Activations