© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10481
    Prev
    Next
    INDEX
    Explanations

    trees and forests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     normas
    0.83
    укра
    0.82
    arsenic
    0.81
    ">+
    0.80
    hmC
    0.80
    MM
    0.79
    ɳ
    0.79
     клу
    0.78
     Julio
    0.78
    ToPlot
    0.78
    POSITIVE LOGITS
     trees
    2.09
     tree
    1.96
    tree
    1.81
    trees
    1.76
     Tree
    1.70
     Trees
    1.60
    Tree
    1.58
     forests
    1.57
    Trees
    1.52
    树
    1.52
    Activations Density 0.170%

    No Known Activations