© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1516
    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
    oré
    0.72
    
    0.72
    atás
    0.69
    ٤
    0.69
     ৪৮
    0.69
    🔸
    0.67
    انيه
    0.66
    0.66
     cyclohexane
    0.66
     sans
    0.66
    POSITIVE LOGITS
            
    2.01
     Seven
    1.67
    Seven
    1.60
     seven
    1.56
    七
    1.51
     tujuh
    1.50
    seven
    1.41
     七
    1.40
     هفت
    1.27
    7
    1.27
    Activations Density 0.215%

    No Known Activations