© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 733
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    <0xC2>
    1.13
    <0xE2>
    0.97
    
    0.95
      
    0.94
     Throughout
    0.91
     (“
    0.91
    both
    0.88
     [
    0.88
     北欧
    0.87
     (…)
    0.87
    POSITIVE LOGITS
     criticisms
    1.71
     disagreements
    1.60
     criticism
    1.59
     prejudices
    1.57
     advantages
    1.56
     objections
    1.56
     difficulties
    1.55
     discussions
    1.55
     hardships
    1.54
     problems
    1.53
    Activations Density 11.504%

    No Known Activations