© 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. 34-GEMMASCOPE-RES-131K
    7. 106333
    Prev
    Next
    INDEX
    Explanations

    movement and action 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ərbaycan
    -0.95
    Patience
    -0.88
    isset
    -0.87
     boredom
    -0.87
    Slowly
    -0.82
    пора
    -0.80
    ktive
    -0.80
     Walking
    -0.80
     smirk
    -0.80
     intimid
    -0.79
    POSITIVE LOGITS
     rushed
    2.78
     rushing
    2.63
     rush
    2.48
     raced
    2.28
     running
    2.27
     hurried
    2.25
     rushes
    2.08
     hurriedly
    2.00
     racing
    1.89
     haste
    1.88
    Activations Density 0.023%

    No Known Activations