© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34193
    Prev
    Next
    INDEX
    Explanations

    conditional statements `if`

    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
    ι
    -0.95
     mã
    -0.78
    ТЬ
    -0.77
     recombinant
    -0.76
    ᴏ
    -0.75
    ᠨ
    -0.74
    upuesto
    -0.74
    Starter
    -0.74
    ToPoint
    -0.73
     sayfas
    -0.72
    POSITIVE LOGITS
     if
    1.60
     если
    1.16
     If
    1.11
    if
    1.08
     якщо
    0.98
     ถ้า
    0.96
     如果
    0.95
    If
    0.95
     هل
    0.94
     אם
    0.94
    Activations Density 0.042%

    No Known Activations