© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48164
    Prev
    Next
    INDEX
    Explanations

    de after certain 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_34/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
    OfThe
    -1.86
     ofthe
    -1.66
    ofthe
    -1.49
     élastique
    -1.05
    ázat
    -1.00
    Postup
    -0.99
     кілька
    -0.99
    创建一个
    -0.95
    zyka
    -0.94
    几个
    -0.93
    POSITIVE LOGITS
     of
    6.16
     de
    2.08
    of
    1.10
     d
    1.01
    cosse
    1.00
     של
    0.94
     my
    0.93
     Of
    0.93
     from
    0.91
     телефону
    0.85
    Activations Density 0.011%

    No Known Activations