© 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. 64475
    Prev
    Next
    INDEX
    Explanations

    code punctuation and structures

    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
    suit
    -0.98
    ALITY
    -0.83
    Children
    -0.78
    thée
    -0.77
    5
    -0.75
    INCE
    -0.75
    Women
    -0.74
    而是
    -0.74
    uite
    -0.74
    思う
    -0.74
    POSITIVE LOGITS
    akang
    1.00
    这段
    0.94
    ostructures
    0.93
    帷
    0.91
     marginBottom
    0.91
     después
    0.88
    Depois
    0.88
     principales
    0.86
     fontWeight
    0.86
    Конечно
    0.86
    Activations Density 0.004%

    No Known Activations