© 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. 130290
    Prev
    Next
    INDEX
    Explanations

    while loop

    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
     already
    -1.60
     therefore
    -1.52
     predominantly
    -1.49
     currently
    -1.48
     then
    -1.46
    RTLD
    -1.41
    ↵↵
    -1.41
     ligera
    -1.41
     soon
    -1.38
     thus
    -1.37
    POSITIVE LOGITS
     with
    1.53
    沨
    1.49
    tively
    1.46
    lihood
    1.41
     through
    1.38
    alisation
    1.34
    邃
    1.34
     on
    1.34
     збіль
    1.33
    :'#
    1.30
    Activations Density 0.009%

    No Known Activations