© 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. 124682
    Prev
    Next
    INDEX
    Explanations

    TL abbreviations

    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
    䊉
    -2.86
    쨩
    -2.81
    {
    -2.80
    barcelona
    -2.67
     uſed
    -2.61
    '
    -2.50
    䊏
    -2.47
    橚
    -2.34
     denominado
    -2.34
     delineated
    -2.34
    POSITIVE LOGITS
    s
    3.41
    en
    3.09
    l
    2.95
    K
    2.64
    н
    2.44
    EN
    2.42
    _
    2.34
    在我
    2.31
    Y
    2.30
    or
    2.28
    Activations Density 0.003%

    No Known Activations