© 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. 65626
    Prev
    Next
    INDEX
    Explanations

    boolean values and control flow

    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
    रीदारी
    -1.03
     daarom
    -0.85
     münchen
    -0.84
    kø
    -0.83
    MANAGEMENT
    -0.83
     肌
    -0.82
    LABOR
    -0.82
     BOU
    -0.81
    📀
    -0.80
    欷
    -0.80
    POSITIVE LOGITS
     Verlet
    0.81
    ocate
    0.81
    ท
    0.80
     Weeknd
    0.79
     aten
    0.79
    今年も
    0.78
     no
    0.77
    熊猫
    0.77
     Schüler
    0.77
     contentment
    0.77
    Activations Density 0.003%

    No Known Activations