© 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. 79388
    Prev
    Next
    INDEX
    Explanations

    sql table and column references

    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
     intoxicating
    -0.85
     Toward
    -0.80
     будь
    -0.78
    Andrzej
    -0.76
    Towards
    -0.75
     addictive
    -0.75
     району
    -0.75
     thủy
    -0.75
     drowsiness
    -0.74
     warms
    -0.73
    POSITIVE LOGITS
     tbl
    1.16
     table
    1.09
    tbl
    1.04
    lookup
    0.95
     tableName
    0.89
    läufer
    0.86
    vw
    0.86
    tableName
    0.86
     lookup
    0.82
    abelle
    0.74
    Activations Density 0.122%

    No Known Activations