© 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. 69920
    Prev
    Next
    INDEX
    Explanations

    Christian Science Monitor

    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
     mantend
    -0.71
     வரு
    -0.71
    jedis
    -0.69
    точный
    -0.68
    instantiate
    -0.68
     Year
    -0.68
    搬
    -0.67
     ۱۴۰۰
    -0.65
     funguje
    -0.65
     Perfect
    -0.64
    POSITIVE LOGITS
     Monitor
    0.87
    Monitor
    0.85
     monitor
    0.82
    MONITOR
    0.80
    monitor
    0.73
    名は
    0.73
     Helle
    0.72
     Kanto
    0.72
    inom
    0.72
     robi
    0.70
    Activations Density 0.037%

    No Known Activations