© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118607
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     lyder
    -0.78
     best
    -0.76
     захворю
    -0.73
    луч
    -0.73
    DEPARTMENT
    -0.72
    ctp
    -0.70
     Aung
    -0.69
    sible
    -0.69
    ⌄
    -0.68
    Stored
    -0.67
    POSITIVE LOGITS
    加拿大
    0.80
     purchases
    0.78
    ardige
    0.78
     餐
    0.76
    餐
    0.73
    ڕ
    0.72
    Ры
    0.70
    走行
    0.69
    DAILY
    0.68
     Cak
    0.68
    Activations Density 0.038%

    No Known Activations