© 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. 6887
    Prev
    Next
    INDEX
    Explanations

    make a case for

    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
    趼
    -1.69
    Приготовление
    -1.66
     pokoje
    -1.61
    ྅
    -1.53
    鈊
    -1.53
    Več
    -1.50
     fabricación
    -1.49
    hörer
    -1.46
     作り方
    -1.45
    büro
    -1.45
    POSITIVE LOGITS
    ing
    1.88
     entanto
    1.56
    蓠
    1.55
     asserts
    1.52
     that
    1.51
    􀂃
    1.45
    从来没有
    1.45
    ar
    1.42
     argument
    1.41
    os
    1.39
    Activations Density 0.027%

    No Known Activations