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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11523
    Prev
    Next
    INDEX
    Explanations

    if 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
    sə
    -1.06
     incess
    -1.05
    tails
    -0.95
    gameserver
    -0.93
     dati
    -0.93
     dito
    -0.93
     ۱۶
    -0.93
     recenti
    -0.92
     alvo
    -0.91
    rages
    -0.91
    POSITIVE LOGITS
     if
    2.00
     если
    1.23
    if
    1.13
     Если
    0.99
     determine
    0.98
     kệ
    0.97
     оно
    0.97
    知ら
    0.96
     若
    0.94
     decide
    0.93
    Activations Density 0.006%

    No Known Activations