© 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. 109111
    Prev
    Next
    INDEX
    Explanations

    being and existence

    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
    ROIT
    -0.80
    glfw
    -0.80
     Nachhaltigkeit
    -0.74
    br
    -0.73
    바
    -0.72
    袭击
    -0.71
    timacy
    -0.71
     pracu
    -0.70
     Senhor
    -0.70
    Built
    -0.69
    POSITIVE LOGITS
     being
    3.06
     Being
    2.64
     existence
    2.55
    Being
    2.31
     быть
    2.30
    being
    2.02
     essere
    1.99
     BEING
    1.99
     être
    1.87
    existence
    1.80
    Activations Density 0.035%

    No Known Activations