© 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. 10-GEMMASCOPE-RES-131K
    4. 87157
    Prev
    Next
    INDEX
    Explanations

    September in dates

    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
     当
    -2.80
    !"
    -2.66
    AddTagHelper
    -2.52
    撳
    -2.42
     upbeat
    -2.36
    aneamente
    -2.22
    nambuco
    -2.16
     svých
    -2.16
     es
    -2.14
    читайте
    -2.14
    POSITIVE LOGITS
    ↵
    4.22
     \
    2.94
    鯡
    2.56
    想了想
    2.56
    which
    2.41
    旁邊
    2.34
    趼
    2.30
    があるので
    2.27
     Our
    2.25
     verbess
    2.23
    Activations Density 0.013%

    No Known Activations