© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33076
    Prev
    Next
    INDEX
    Explanations

    puzzle, brain teaser, logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    虛
    -0.82
     kilomet
    -0.76
     Fears
    -0.75
    idas
    -0.73
     xay
    -0.73
    escent
    -0.73
    Sinh
    -0.73
    raeli
    -0.73
    margin
    -0.71
    inflammatory
    -0.71
    POSITIVE LOGITS
     puzzle
    2.52
     puzzles
    2.39
     brain
    2.38
     logic
    2.08
    puzzle
    1.90
     riddles
    1.90
    brain
    1.88
     Brain
    1.82
    Puzzle
    1.79
     Logic
    1.78
    Activations Density 0.066%

    No Known Activations