© 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. 197381
    Prev
    Next
    INDEX
    Explanations

    dating, advancement, wed, divorce, age

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

    age gap

    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
     néhány
    0.61
    ij
    0.56
     극한
    0.53
     különböző
    0.52
    ⓡ
    0.51
     zarówno
    0.51
     මෙම
    0.50
     በጣም
    0.49
     sowohl
    0.49
     उमेदवार
    0.49
    POSITIVE LOGITS
    AGE
    0.52
    IF
    0.51
    ARY
    0.51
    뭡
    0.51
     Financing
    0.50
    LIFE
    0.50
    ?
    0.50
    ON
    0.48
    ?"
    0.48
     Divorce
    0.48
    Activations Density 0.001%

    No Known Activations