© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8278
    Prev
    Next
    INDEX
    Explanations

    undergraduate students, lawyers, artists

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

    personal statements about self

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     monies
    0.69
    と言う
    0.60
     BTW
    0.59
     hubby
    0.58
    믄
    0.55
    咱們
    0.53
    BTW
    0.53
    🤣🤣
    0.52
     tuff
    0.50
     thru
    0.50
    POSITIVE LOGITS
     Undergraduate
    0.75
     undergraduate
    0.61
     undergraduates
    0.59
    实习
    0.58
     alumna
    0.55
    留学
    0.55
     সত্ত্বেও
    0.54
     вследствие
    0.54
     “[
    0.54
     alumnus
    0.54
    Activations Density 0.345%

    No Known Activations