© 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. 22-GEMMASCOPE-RES-131K
    7. 71277
    Prev
    Next
    INDEX
    Explanations

    first mention

    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_22/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
    现在的
    -1.00
    Originally
    -0.98
    一直
    -0.96
    最新
    -0.96
    formerly
    -0.94
     nuevamente
    -0.93
    以前
    -0.93
     Maintenant
    -0.91
    希望
    -0.91
    近年来
    -0.90
    POSITIVE LOGITS
     earliest
    2.05
     first
    2.05
     اولین
    1.73
     ensimmä
    1.60
     eerste
    1.55
    Erste
    1.52
     pioneer
    1.49
     erste
    1.49
     első
    1.49
     πρώ
    1.48
    Activations Density 0.125%

    No Known Activations