© 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. 22-GEMMASCOPE-RES-131K
    4. 27952
    Prev
    Next
    INDEX
    Explanations

    names of people or theories

    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
     they
    -1.07
    unjung
    -1.04
     currently
    -0.99
     They
    -0.98
     recently
    -0.98
     않았
    -0.95
    eleven
    -0.94
     प्रश्न
    -0.94
    oblo
    -0.93
    recent
    -0.92
    POSITIVE LOGITS
     decades
    1.25
     ссыл
    1.13
     classic
    1.13
    ഢ
    1.02
     xưa
    1.02
     Tó
    1.02
    经典
    1.02
    龛
    0.98
     ۱۳
    0.98
     legend
    0.98
    Activations Density 0.025%

    No Known Activations