© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21127
    Prev
    Next
    INDEX
    Explanations

    while + -ing verbs

    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
     after
    -2.38
     as
    -2.16
     would
    -2.00
     when
    -1.91
     began
    -1.80
     before
    -1.73
     came
    -1.73
     in
    -1.71
     get
    -1.69
     could
    -1.66
    POSITIVE LOGITS
    跑去
    1.70
    亍
    1.65
    暗暗
    1.62
    珦
    1.59
     televiz
    1.57
     Também
    1.56
    裢
    1.56
    ariously
    1.55
     your
    1.55
    蘩
    1.54
    Activations Density 0.017%

    No Known Activations