© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98222
    Prev
    Next
    INDEX
    Explanations

    Q: followed by question

    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
     sesta
    -0.80
     ダイ
    -0.74
     while
    -0.69
     života
    -0.69
     acquaintances
    -0.69
     nodded
    -0.67
     Combining
    -0.67
    builds
    -0.66
    ילו
    -0.66
     started
    -0.66
    POSITIVE LOGITS
    Abra
    0.77
     голу
    0.75
    omycin
    0.75
    visiae
    0.75
    ⁻
    0.74
    ншот
    0.72
    дная
    0.72
     pourrait
    0.70
     zon
    0.69
     العديد
    0.69
    Activations Density 0.019%

    No Known Activations