© 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. 22-GEMMASCOPE-RES-131K
    7. 24904
    Prev
    Next
    INDEX
    Explanations

    programming keywords and symbols

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     would
    -1.22
     not
    -1.15
    
    -1.10
     did
    -1.10
     Although
    -1.07
    ↵
    -1.06
     problems
    -1.05
    чиком
    -1.05
     This
    -1.05
     February
    -1.05
    POSITIVE LOGITS
    
    1.31
     maniere
    1.26
     poivre
    1.25
     gâ
    1.20
    iencing
    1.20
    ܖ
    1.20
    〬
    1.19
    焢
    1.19
     薬局
    1.19
    Aho
    1.19
    Activations Density 0.000%

    No Known Activations