© 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. 10-GEMMASCOPE-RES-131K
    7. 130392
    Prev
    Next
    INDEX
    Explanations

    When I was

    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_10/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
     if
    -2.08
     Also
    -1.86
     for
    -1.79
     with
    -1.76
    This
    -1.75
     גם
    -1.74
    That
    -1.72
     أيضا
    -1.71
     This
    -1.71
     because
    -1.66
    POSITIVE LOGITS
     remarkably
    1.80
    螣
    1.77
     wonderfully
    1.72
    ”
    1.72
     a
    1.70
    苤
    1.67
     bästa
    1.64
    吒
    1.62
     ſont
    1.60
    一个小
    1.59
    Activations Density 0.019%

    No Known Activations