© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 734
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     violated
    1.12
     Suppose
    1.05
    [!
    1.05
    cities
    1.04
     presupp
    0.99
    Suppose
    0.98
     perpetrated
    0.96
     violating
    0.95
    [
    0.95
     transgress
    0.94
    POSITIVE LOGITS
     versatile
    1.74
     panoramic
    1.69
     roomy
    1.61
     elegant
    1.57
     spacious
    1.56
     elegante
    1.55
     kitchenette
    1.52
    多彩
    1.50
     adjustable
    1.49
     tastefully
    1.47
    Activations Density 2.603%

    No Known Activations