© 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. 10-GEMMASCOPE-RES-131K
    4. 11589
    Prev
    Next
    INDEX
    Explanations

    prefacing an action or topic discussion

    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
     уже
    -1.27
     именно
    -1.27
    also
    -1.22
     حتی
    -1.20
    already
    -1.16
     Поэтому
    -1.13
     даже
    -1.13
     dopiero
    -1.13
    Already
    -1.11
     where
    -1.09
    POSITIVE LOGITS
     we
    1.57
    5
    1.48
     then
    1.39
    8
    1.36
    middels
    1.33
     here
    1.28
     eines
    1.27
     aarde
    1.26
     наша
    1.24
     riport
    1.23
    Activations Density 0.019%

    No Known Activations