© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48803
    Prev
    Next
    INDEX
    Explanations

    puzzle variants

    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
     reading
    -0.75
     check
    -0.74
    ayette
    -0.73
    hero
    -0.73
     cinemat
    -0.73
     superhero
    -0.72
     rich
    -0.70
     Mand
    -0.70
     orange
    -0.69
     cinema
    -0.69
    POSITIVE LOGITS
     puzzle
    0.94
     Variants
    0.93
    Puzzle
    0.88
     Sudoku
    0.84
     Valk
    0.83
    variants
    0.83
     demonios
    0.82
     голо
    0.82
     Leighton
    0.81
     puzz
    0.80
    Activations Density 0.031%

    No Known Activations