© 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. 64640
    Prev
    Next
    INDEX
    Explanations

    if clauses

    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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.26
     of
    -1.16
    után
    -1.02
    matician
    -1.01
    را
    -0.98
     FontWeight
    -0.96
     a
    -0.95
    )$_
    -0.94
     up
    -0.93
    
    -0.93
    POSITIVE LOGITS
     إذا
    0.98
    及び
    0.97
    已經
    0.95
     если
    0.95
     якщо
    0.93
     nếu
    0.92
    相當
    0.87
     them
    0.86
     rilass
    0.85
    ńcu
    0.84
    Activations Density 0.010%

    No Known Activations