© 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. 47197
    Prev
    Next
    INDEX
    Explanations

    special characters and code constructs

    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
    Another
    -1.21
    お楽しみに
    -1.19
    peł
    -1.13
    　↓
    -1.10
    toDouble
    -1.09
     Dostupné
    -1.08
    に戻る
    -1.02
    うわ
    -1.02
    $.}
    -1.01
    视着
    -1.01
    POSITIVE LOGITS
     .........
    1.13
     และ
    1.13
     ..............
    1.06
     ...........
    1.05
    ______________
    1.05
    ___________
    0.99
     .............
    0.98
     ...............
    0.98
    และ
    0.97
     molti
    0.97
    Activations Density 0.284%

    No Known Activations