© 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. 251774
    Prev
    Next
    INDEX
    Explanations

    married to or marriage of

    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
    গ
    0.48
    webContents
    0.48
    keyList
    0.46
    ト
    0.46
    answers
    0.44
    кта
    0.44
     Erek
    0.42
     OCTOBER
    0.42
    cord
    0.42
    }\|^{
    0.41
    POSITIVE LOGITS
     शादी
    0.57
     marriage
    0.52
    婚姻
    0.52
     Marriage
    0.51
     Married
    0.50
    婚
    0.49
     matrim
    0.49
     Merry
    0.48
     결혼
    0.48
     thuần
    0.48
    Activations Density 0.016%

    No Known Activations