© 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. 41459
    Prev
    Next
    INDEX
    Explanations

    Dale and Darren names

    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
    迥
    -2.59
    contd
    -2.52
     of
    -2.41
    弍
    -2.41
     leaſt
    -2.41
    以上就是
    -2.39
    下一篇
    -2.38
    DETAILED
    -2.38
    ⮚
    -2.38
     resolves
    -2.36
    POSITIVE LOGITS
    </b>
    2.83
    an
    2.75
    o
    2.73
    <
    2.50
    [
    2.48
    {
    2.45
    of
    2.39
     schlechte
    2.36
    ꪹ
    2.33
     the
    2.22
    Activations Density 0.002%

    No Known Activations