© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38668
    Prev
    Next
    INDEX
    Explanations

    best, greatest, available

    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_22/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
    ζει
    -1.02
    hysema
    -1.01
     felicitación
    -0.96
     první
    -0.95
     revolución
    -0.95
    joueurs
    -0.92
     číslo
    -0.92
    isante
    -0.92
    БИ
    -0.91
    дожник
    -0.90
    POSITIVE LOGITS
     best
    1.27
     migliori
    1.21
     maximum
    1.19
     available
    1.19
     utmost
    1.05
     terbaik
    1.03
     максимально
    1.02
     greatest
    1.02
     лучших
    1.02
     finest
    1.00
    Activations Density 0.039%

    No Known Activations