© 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. 22-GEMMASCOPE-RES-131K
    7. 93346
    Prev
    Next
    INDEX
    Explanations

    great followed by nouns

    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
    簡介
    -1.76
     asfal
    -1.74
    後記
    -1.72
    jmu
    -1.70
    ⤥
    -1.69
    مقدمه
    -1.66
    戗
    -1.64
    際には
    -1.62
    皷
    -1.61
    Willkommen
    -1.59
    POSITIVE LOGITS
    !
    2.14
    [
    1.93
     '
    1.81
    new
    1.77
    a
    1.67
    Just
    1.65
    .
    1.62
     .
    1.62
    ('
    1.60
    ."
    1.58
    Activations Density 0.024%

    No Known Activations