© 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. 56137
    Prev
    Next
    INDEX
    Explanations

    come to life

    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
     prospect
    -0.77
     nén
    -0.73
    olan
    -0.73
     sẵn
    -0.72
    gross
    -0.70
    őd
    -0.68
    nitř
    -0.68
    beach
    -0.68
     Yaman
    -0.68
     reagiert
    -0.67
    POSITIVE LOGITS
     alive
    3.20
     life
    2.38
     Alive
    2.03
    alive
    1.99
    life
    1.79
     vida
    1.77
    Alive
    1.77
     LIFE
    1.74
     ALIVE
    1.73
    Life
    1.70
    Activations Density 0.019%

    No Known Activations