© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3885
    Prev
    Next
    INDEX
    Explanations

    tree data structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     McMahon
    1.17
    Gamb
    1.17
     الجز
    1.05
    сь
    1.03
     ڤ
    1.03
    ڤ
    1.00
    면
    0.99
     čin
    0.98
    馔
    0.98
     Currie
    0.97
    POSITIVE LOGITS
     tree
    2.82
     TREE
    2.80
     trees
    2.76
     Tree
    2.71
    Trees
    2.64
     Trees
    2.63
    TREE
    2.62
    Tree
    2.55
    trees
    2.54
    tree
    2.36
    Activations Density 0.127%

    No Known Activations