© 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. 10-GEMMASCOPE-RES-131K
    7. 60243
    Prev
    Next
    INDEX
    Explanations

    the word or term

    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
     and
    -2.25
    鈊
    -1.97
    なども
    -1.83
    の前
    -1.80
    ."
    -1.76
    脔
    -1.75
     tohoto
    -1.73
     různých
    -1.73
    jangkau
    -1.72
    苼
    -1.72
    POSITIVE LOGITS
     a
    1.95
     hvor
    1.79
     “
    1.76
     では
    1.74
     tersenyum
    1.69
     menyadari
    1.63
    re
    1.63
     “(
    1.61
     sebagai
    1.57
     太郎
    1.55
    Activations Density 0.048%

    No Known Activations