© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178271
    Prev
    Next
    INDEX
    Explanations

    health-related quality of life marathon

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

    list item prefix

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    小孩
    0.57
    Сі
    0.49
    产生
    0.47
    perplexity
    0.46
    다면
    0.45
    细菌
    0.45
    Assertion
    0.45
    ០
    0.45
    otherArchive
    0.44
    눗
    0.44
    POSITIVE LOGITS
     mitig
    0.48
     recommandé
    0.47
     evolving
    0.45
     åp
    0.45
     satisfies
    0.45
     ensures
    0.44
     forêt
    0.44
     mitigate
    0.43
    .).
    0.42
     ceremonia
    0.42
    Activations Density 0.000%

    No Known Activations