© 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. 6842
    Prev
    Next
    INDEX
    Explanations

    geological time periods

    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
    憮
    -1.96
    廰
    -1.94
    formatics
    -1.88
    そういえば
    -1.76
    うーん
    -1.75
     the
    -1.73
    屨
    -1.73
    尨
    -1.68
    头顶
    -1.66
    慣れて
    -1.64
    POSITIVE LOGITS
    、
    1.91
    他
    1.61
    จะ
    1.59
    '
    1.54
    ↵
    1.49
     vorigen
    1.45
    新
    1.45
    而
    1.42
    ”、“
    1.41
    .
    1.41
    Activations Density 0.013%

    No Known Activations