© 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-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 991
    Prev
    Next
    INDEX
    Explanations

    past participle verbs after auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     jis
    0.40
     asso
    0.40
     floribus
    0.39
     gioco
    0.38
     تكونوا
    0.38
     rmse
    0.38
     servicio
    0.38
     suốt
    0.37
    ிரி
    0.36
    输
    0.35
    POSITIVE LOGITS
    strategy
    0.40
     authorize
    0.39
     intens
    0.38
     launched
    0.37
    ରା
    0.37
    intens
    0.36
     Strategy
    0.36
    Revised
    0.36
    donor
    0.36
     stressing
    0.36
    Activations Density 0.020%

    No Known Activations