© 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. 34-GEMMASCOPE-RES-131K
    7. 62380
    Prev
    Next
    INDEX
    Explanations

    identifying factors, issues, or opportunities

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bruin
    -1.21
    ANDRA
    -1.09
     adem
    -1.09
     harde
    -1.05
    ffichage
    -1.04
     выбран
    -1.04
     membrana
    -1.03
     suporta
    -1.02
     estudantes
    -1.02
     salari
    -1.01
    POSITIVE LOGITS
     areas
    2.00
     potential
    1.95
     suitable
    1.88
     where
    1.84
     key
    1.70
     those
    1.70
     trends
    1.69
     which
    1.64
    哪些
    1.61
     likely
    1.52
    Activations Density 0.129%

    No Known Activations