© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6830
    Prev
    Next
    INDEX
    Explanations

    transition words and phrases

    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
    Negative Logits
     or
    -2.23
     using
    -2.06
     as
    -2.03
     all
    -1.94
     like
    -1.84
     would
    -1.84
     first
    -1.80
     from
    -1.67
     one
    -1.63
     took
    -1.61
    POSITIVE LOGITS
     手绘
    1.59
     fidé
    1.45
     Quando
    1.45
     diriger
    1.38
    Когда
    1.38
    お花
    1.37
    籏
    1.35
    畱
    1.35
     этих
    1.34
     όταν
    1.34
    Activations Density 0.223%

    No Known Activations