© 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. 79197
    Prev
    Next
    INDEX
    Explanations

    national heritage, chief executive, breaking news

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Zon
    -0.68
     jeopardize
    -0.67
    '>";
    -0.67
    竞技
    -0.66
     проти
    -0.66
    ıl
    -0.66
     الرحمن
    -0.66
    愈
    -0.66
     (`
    -0.66
    OfMonth
    -0.65
    POSITIVE LOGITS
    BITDA
    0.85
    rijf
    0.84
    cataly
    0.82
    δρ
    0.79
     southbound
    0.77
    TEE
    0.77
    GROUP
    0.76
     Trustee
    0.74
    arat
    0.73
    gdb
    0.73
    Activations Density 0.014%

    No Known Activations