© 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. 34-GEMMASCOPE-RES-131K
    7. 81536
    Prev
    Next
    INDEX
    Explanations

    existence statements

    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
     ਲਈ
    -0.82
    ු
    -0.75
    utc
    -0.74
     aren
    -0.71
    <0x90>
    -0.69
     jemand
    -0.69
    стройки
    -0.68
     primarily
    -0.68
     природ
    -0.68
    益
    -0.67
    POSITIVE LOGITS
     existence
    1.98
     exists
    1.56
    是否存在
    1.55
     exist
    1.48
    不存在
    1.46
    exists
    1.45
     существо
    1.41
    存在
    1.36
     existi
    1.35
    does
    1.32
    Activations Density 0.068%

    No Known Activations