© 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. 58086
    Prev
    Next
    INDEX
    Explanations

    code type declarations

    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
     causando
    -1.66
     
    -1.49
     entrando
    -1.48
     provocando
    -1.45
     indicando
    -1.37
     mirando
    -1.34
    俨
    -1.32
     destinados
    -1.30
     formando
    -1.30
    一丝
    -1.30
    POSITIVE LOGITS
     of
    2.31
     by
    1.59
     like
    1.56
     興
    1.38
    AGEMENT
    1.34
    栻
    1.32
     女孩
    1.30
    ETIES
    1.28
     sorella
    1.27
     from
    1.27
    Activations Density 0.042%

    No Known Activations