© 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. 63331
    Prev
    Next
    INDEX
    Explanations

    laid or lays

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

    lay foundation or groundwork

    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
     unruly
    0.54
     scram
    0.46
     pej
    0.43
    𝙈
    0.42
     Madeleine
    0.42
     campaigner
    0.41
     dépour
    0.41
    澥
    0.40
     scramble
    0.39
     stationed
    0.39
    POSITIVE LOGITS
    estre
    0.42
    fn
    0.41
    겅
    0.41
    incub
    0.41
    astri
    0.40
    fp
    0.39
    hw
    0.39
    atlas
    0.38
    gulp
    0.38
     Incub
    0.38
    Activations Density 0.008%

    No Known Activations