© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87142
    Prev
    Next
    INDEX
    Explanations

    upon event introduction

    np_acts-logits-general · gemini-2.5-flash-lite

    upon / when followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     convuls
    0.55
    镶
    0.52
     لوبو
    0.50
    V
    0.50
    务
    0.50
     बनाम
    0.49
    務
    0.48
     Vereinigte
    0.47
    와
    0.47
    岗位
    0.47
    POSITIVE LOGITS
     Attempt
    0.55
     attempt
    0.50
     überprü
    0.50
     überprüfen
    0.50
     arrival
    0.49
     weitere
    0.48
     попы
    0.48
     examination
    0.47
     attempting
    0.46
     স্বীকার
    0.46
    Activations Density 0.041%

    No Known Activations