© 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. 56705
    Prev
    Next
    INDEX
    Explanations

    verb followed by "up"

    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
    Out
    -1.02
    Up
    -0.93
    Off
    -0.88
     Out
    -0.83
    Down
    -0.82
    out
    -0.81
    OutOf
    -0.79
     Elderly
    -0.76
     genes
    -0.72
    )}=\
    -0.72
    POSITIVE LOGITS
     weder
    0.77
    Mga
    0.74
    vacy
    0.74
    ânea
    0.74
     william
    0.73
     bede
    0.71
     bestand
    0.70
    没有了
    0.70
    nání
    0.69
     teg
    0.69
    Activations Density 0.054%

    No Known Activations