© 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. 8182
    Prev
    Next
    INDEX
    Explanations

    court case filings & headers

    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
     этой
    -2.03
     этого
    -1.90
     این
    -1.59
    ↵↵
    -1.57
    んびり
    -1.55
    鬟
    -1.53
     этим
    -1.52
     także
    -1.51
     этот
    -1.51
     and
    -1.51
    POSITIVE LOGITS
    out
    1.56
    ers
    1.56
     Of
    1.55
    al
    1.52
    ra
    1.51
     his
    1.47
    he
    1.45
    z
    1.43
    ....
    1.43
    sierung
    1.41
    Activations Density 0.006%

    No Known Activations