© 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-16K
    7. 11588
    Prev
    Next
    INDEX
    Explanations

    to be + past participle

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

    verbs after "to"

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tica
    0.53
     jemand
    0.48
    cante
    0.48
    సా
    0.48
     Forschung
    0.48
    $
    0.47
    نر
    0.47
    تان
    0.46
    簇
    0.46
    ව
    0.45
    POSITIVE LOGITS
     be
    0.83
     give
    0.57
     supposed
    0.55
     beware
    0.55
     replace
    0.52
     apply
    0.51
     வழங்கப்படும்
    0.51
     become
    0.51
    ToBe
    0.51
     minimize
    0.50
    Activations Density 0.166%

    No Known Activations