© 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. 30115
    Prev
    Next
    INDEX
    Explanations

    various devices and conditions

    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
     and
    -2.63
     both
    -1.92
    Both
    -1.90
     beiden
    -1.64
     two
    -1.63
     Both
    -1.61
     or
    -1.45
    両
    -1.45
    这两个
    -1.38
     duo
    -1.37
    POSITIVE LOGITS
     etc
    1.74
    etc
    1.73
     conster
    1.70
     all
    1.67
     tất
    1.60
    among
    1.57
    どれも
    1.55
     semuanya
    1.54
    など
    1.52
     statut
    1.52
    Activations Density 0.251%

    No Known Activations