© 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. 25099
    Prev
    Next
    INDEX
    Explanations

    code or programming 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     constantemente
    -0.97
     fără
    -0.96
    !="
    -0.93
    几种
    -0.93
    茛
    -0.86
    notas
    -0.86
    各种
    -0.86
    ''')
    -0.85
    ']=$
    -0.83
    ⌀
    -0.82
    POSITIVE LOGITS
     now
    1.16
     then
    1.14
     afterward
    0.92
     thereafter
    0.91
     afterwards
    0.90
     once
    0.89
     smaller
    0.88
     poliéster
    0.88
    gment
    0.88
     week
    0.88
    Activations Density 0.001%

    No Known Activations