© 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. 56716
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by specific nouns

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

    Google Account

    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
    刨
    0.53
    ຜະລິດຕະພັນ
    0.51
    내가
    0.50
    过来的
    0.50
    рті
    0.50
    Referensi
    0.50
    টসঅ্যাপ
    0.49
     시절
    0.49
    строва
    0.49
    구매
    0.49
    POSITIVE LOGITS
     $
    0.55
    ws
    0.54
     WS
    0.52
     .
    0.51
     man
    0.50
    na
    0.50
     Jew
    0.50
     \
    0.50
    ä
    0.50
     ,
    0.50
    Activations Density 0.000%

    No Known Activations