© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83000
    Prev
    Next
    INDEX
    Explanations

    choice and decision making

    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_34/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
    instead
    -0.84
     normale
    -0.81
     beim
    -0.81
     saine
    -0.80
     normales
    -0.79
     zodat
    -0.79
    了不少
    -0.79
     Natur
    -0.78
     uden
    -0.78
     majd
    -0.77
    POSITIVE LOGITS
     choices
    1.95
     choice
    1.70
     chooses
    1.57
     choose
    1.52
     decisions
    1.42
    選擇
    1.40
    CHOICE
    1.33
     determines
    1.29
     Choices
    1.23
    choices
    1.22
    Activations Density 0.056%

    No Known Activations