© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22637
    Prev
    Next
    INDEX
    Explanations

    more than

    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
    Negative Logits
    '
    -1.74
     it
    -1.57
    section
    -1.41
    除此
    -1.35
    mittances
    -1.30
    نامج
    -1.28
    crl
    -1.27
    ebenarnya
    -1.24
     hà
    -1.23
    الو
    -1.23
    POSITIVE LOGITS
     than
    1.61
    abancı
    1.58
    数据
    1.58
    The
    1.54
     embl
    1.51
     aspetti
    1.50
    鲮
    1.46
    珦
    1.45
    Szia
    1.45
     legte
    1.38
    Activations Density 0.023%

    No Known Activations