© 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. 123778
    Prev
    Next
    INDEX
    Explanations

    separators and symbols

    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
     upheaval
    -1.66
    <bos>
    -1.51
     mergul
    -1.46
    錼
    -1.45
     atrav
    -1.41
    ar
    -1.40
    很想
    -1.38
    殇
    -1.38
    "
    -1.38
     mehreren
    -1.37
    POSITIVE LOGITS
    祧
    2.17
    鹇
    1.80
    葙
    1.77
     of
    1.74
     tramont
    1.68
    wości
    1.63
     hende
    1.62
    毉
    1.61
     juſ
    1.60
    ！】
    1.60
    Activations Density 0.013%

    No Known Activations