© 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. 99584
    Prev
    Next
    INDEX
    Explanations

    temporal sequence markers, place names, foreign words

    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
    (
    -2.77
    brtc
    -2.69
     desean
    -2.48
     soñ
    -2.42
     asesin
    -2.42
    淙
    -2.31
    ن
    -2.31
     maravilla
    -2.25
     refugi
    -2.25
     encuentras
    -2.23
    POSITIVE LOGITS
    <bos>
    3.23
    .
    2.61
    ，“
    2.61
    姈
    2.47
    {
    2.36
    ...");
    2.34
    ༵
    2.34
    ycznych
    2.34
    _{
    2.33
    ਗ਼
    2.25
    Activations Density 0.001%

    No Known Activations