© 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. 110884
    Prev
    Next
    INDEX
    Explanations

    each other

    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
    瑧
    -2.16
     the
    -2.09
    焄
    -2.08
     godk
    -1.96
     it
    -1.95
     a
    -1.87
    l
    -1.84
    禑
    -1.84
    嫘
    -1.84
     alebo
    -1.77
    POSITIVE LOGITS
    {
    1.95
    .
    1.90
    说
    1.80
    ’
    1.77
     لأن
    1.67
    Instead
    1.64
    eavor
    1.63
     zout
    1.62
     намного
    1.62
    actéristi
    1.55
    Activations Density 0.013%

    No Known Activations