© 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. 10-GEMMASCOPE-RES-131K
    7. 105918
    Prev
    Next
    INDEX
    Explanations

    dtype, punctuation, assessment, Rox Won

    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_10/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
    瑨
    -2.88
    瑧
    -2.70
    ’,
    -2.53
     использованием
    -2.52
     seminal
    -2.44
    辚
    -2.42
    ୪
    -2.28
     厂
    -2.28
    ーめん
    -2.27
    YNAMIC
    -2.23
    POSITIVE LOGITS
     OGSÅ
    2.47
     verwe
    2.33
     kursi
    2.30
     dtype
    2.23
     bintang
    2.22
     DÍA
    2.19
     untuk
    2.17
     ideen
    2.17
     risiko
    2.14
     gefe
    2.14
    Activations Density 0.001%

    No Known Activations