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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69019
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
     lakini
    -1.01
    DOCT
    -0.88
     batik
    -0.86
     föränd
    -0.82
     kuhusu
    -0.82
     egentligen
    -0.82
    Vinyl
    -0.82
    Geographie
    -0.81
     Lade
    -0.81
     XXVIII
    -0.80
    POSITIVE LOGITS
     if
    3.33
     если
    2.31
     אם
    1.98
     якщо
    1.93
     nếu
    1.91
     اگر
    1.89
    if
    1.84
     If
    1.77
     jeśli
    1.76
     unless
    1.73
    Activations Density 0.065%

    No Known Activations