© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49625
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and expressions using "where"

    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
    ](#
    -0.91
     установить
    -0.90
    之路
    -0.81
    迎
    -0.81
     to
    -0.79
    :[
    -0.76
    一路
    -0.76
    SetOutput
    -0.75
    ›
    -0.74
     Espagne
    -0.74
    POSITIVE LOGITS
     where
    2.44
    where
    2.05
    其中
    1.97
     here
    1.95
    ここで
    1.76
     где
    1.73
    这里的
    1.73
     wobei
    1.59
    Here
    1.56
     wherein
    1.52
    Activations Density 0.056%

    No Known Activations