© 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. 199041
    Prev
    Next
    INDEX
    Explanations

    pay people underestimate

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

    who reports to whom

    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
    ت
    0.59
    конструк
    0.54
    ต
    0.52
    й
    0.49
    سے
    0.48
    т
    0.48
    سین
    0.48
    ла
    0.47
    ть
    0.47
    լ
    0.47
    POSITIVE LOGITS
     Gives
    0.52
     pay
    0.51
     Pay
    0.49
     Believe
    0.48
     Cabernet
    0.48
     Tao
    0.48
     S
    0.48
     U
    0.47
     PAY
    0.47
     Oi
    0.47
    Activations Density 0.000%

    No Known Activations