© 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. 892
    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
     membahas
    0.84
    啟用
    0.80
     বাস্তবায়ন
    0.72
     penerapan
    0.72
     സംവിധ
    0.72
     рецен
    0.71
    فیر
    0.71
    黜
    0.70
     оформи
    0.70
    鎗
    0.70
    POSITIVE LOGITS
     foraging
    1.95
     nesting
    1.79
     mating
    1.78
     nests
    1.76
     roost
    1.74
     predation
    1.64
     habitat
    1.63
     nest
    1.58
     breeding
    1.57
     habitats
    1.55
    Activations Density 0.944%

    No Known Activations