© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11770
    Prev
    Next
    INDEX
    Explanations

    jigsaw puzzles and mysteries

    np_acts-logits-general · gemini-2.5-flash-lite

    jigsaw puzzle or riddle solving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
     truth
    0.39
    truth
    0.39
     strap
    0.38
    kbar
    0.38
     Comerc
    0.38
    ोहित
    0.37
     गण
    0.37
    塁
    0.37
     खनन
    0.36
     veer
    0.36
    POSITIVE LOGITS
     puzzle
    2.22
     puzzles
    2.13
    puzzle
    2.09
     Puzzle
    1.99
    Puzzle
    1.98
     jigsaw
    1.80
     puzz
    1.75
     पजल
    1.58
    🧩
    1.47
     puzzling
    1.37
    Activations Density 0.105%

    No Known Activations