© 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. 22590
    Prev
    Next
    INDEX
    Explanations

    monetary value after worth

    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
    _
    -1.96
    \]
    -1.94
    )_{
    -1.93
    9
    -1.79
    \|_{
    -1.78
    嗇
    -1.75
    la
    -1.74
    7
    -1.73
    ти
    -1.72
    ２
    -1.71
    POSITIVE LOGITS
     the
    2.78
    我们会
    2.17
    此事
    1.95
    雠
    1.88
    衚
    1.78
    娯
    1.77
    スノー
    1.77
    帏
    1.70
    玙
    1.68
    ケーブル
    1.67
    Activations Density 0.004%

    No Known Activations