© 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. 10-GEMMASCOPE-RES-131K
    7. 72212
    Prev
    Next
    INDEX
    Explanations

    code delimiters and specific contexts

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     their
    -1.91
     either
    -1.64
     mereka
    -1.60
     from
    -1.59
     released
    -1.57
     море
    -1.55
     THEIR
    -1.42
    跩
    -1.39
     Their
    -1.39
     ケア
    -1.38
    POSITIVE LOGITS
    2
    2.27
    You
    2.09
    3
    2.02
    4
    1.99
    5
    1.94
    8
    1.89
    9
    1.88
    7
    1.62
    簍
    1.55
    0
    1.54
    Activations Density 0.000%

    No Known Activations