© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1073
    Prev
    Next
    INDEX
    Explanations

    performance and speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sprinkle
    0.68
     kitchenette
    0.68
     invention
    0.67
    awed
    0.67
    diversity
    0.67
     ectopic
    0.65
     spread
    0.65
    )=\{
    0.65
     affiliations
    0.65
     custodian
    0.65
    POSITIVE LOGITS
     performance
    2.02
    Performance
    1.95
     Performance
    1.92
    performance
    1.83
     PERFORMANCE
    1.65
     performans
    1.57
     prestazioni
    1.55
     performances
    1.53
     desempenho
    1.51
    パフォーマンス
    1.50
    Activations Density 2.034%

    No Known Activations