© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75004
    Prev
    Next
    INDEX
    Explanations

    lay down, lay in, lay out

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

    lay out, lay down, lay it on

    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
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.70
    d
    0.62
    ه
    0.57
    д
    0.55
    ü
    0.54
    прав
    0.53
    č
    0.52
    z
    0.52
    ্ধ
    0.49
    ד
    0.49
    POSITIVE LOGITS
     lays
    1.16
     laying
    1.09
     laid
    1.04
     LAY
    0.95
    laying
    0.92
    laid
    0.85
     lay
    0.84
    躺
    0.84
    Lay
    0.82
     Lay
    0.80
    Activations Density 0.070%

    No Known Activations