© 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. 34-GEMMASCOPE-RES-131K
    7. 102943
    Prev
    Next
    INDEX
    Explanations

    introductory "while" clauses

    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
     when
    -1.16
     cuando
    -1.06
     כאשר
    -1.05
     just
    -1.03
     quando
    -1.02
     يعرف
    -1.01
     lesquels
    -1.00
    řízen
    -0.99
    にも
    -0.98
    差不多
    -0.98
    POSITIVE LOGITS
     researching
    1.67
     it
    1.63
     waiting
    1.62
     you
    1.53
     browsing
    1.45
     watching
    1.40
     visiting
    1.35
     awaiting
    1.34
     attending
    1.24
     certamente
    1.22
    Activations Density 0.017%

    No Known Activations