© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34898
    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
    yyb
    -1.07
     czter
    -1.04
     cumplido
    -1.02
    hacia
    -1.02
    ulfon
    -1.02
    ētu
    -1.01
    secara
    -1.01
    헙
    -1.00
    bánh
    -1.00
    feliz
    -0.99
    POSITIVE LOGITS
    !
    0.97
     &
    0.95
     製作
    0.89
    我
    0.89
    月
    0.87
     userRepository
    0.85
    нных
    0.84
    同样
    0.82
    首先
    0.82
    /
    0.81
    Activations Density 0.007%

    No Known Activations