© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12821
    Prev
    Next
    INDEX
    Explanations

    present study/paper/work

    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
     when
    -2.03
     with
    -1.75
     where
    -1.73
     esquecer
    -1.56
     reunir
    -1.55
     determinadas
    -1.40
     for
    -1.35
     ciertas
    -1.35
     everything
    -1.33
     {
    -1.33
    POSITIVE LOGITS
    5
    1.70
    ri
    1.49
     ”
    1.46
    \
    1.45
    更是
    1.45
     ‚
    1.41
     menghubungi
    1.39
    品牌的
    1.39
     ۵
    1.38
     investissements
    1.38
    Activations Density 0.111%

    No Known Activations