© 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. 726
    Prev
    Next
    INDEX
    Explanations

    Universal Studios lot

    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
     県
    -0.84
     Osiris
    -0.75
    ⚒
    -0.71
     じ
    -0.69
    解析
    -0.69
    anja
    -0.67
    TSCA
    -0.67
     milion
    -0.66
     Bik
    -0.66
    含量
    -0.66
    POSITIVE LOGITS
     lot
    3.13
    Lot
    2.61
     Lot
    2.61
    lot
    2.14
     lots
    1.95
     LOT
    1.83
     Lots
    1.77
    Lots
    1.66
    LOT
    1.61
    lots
    1.52
    Activations Density 0.041%

    No Known Activations