© 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. 109284
    Prev
    Next
    INDEX
    Explanations

    families, female, purpose, Notification, possessive 's

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

    Chinese IELTS

    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
     йөкләү
    0.58
     күзгү
    0.57
     ອ
    0.51
     Бүгенге
    0.50
     фаразы
    0.48
     ໜ
    0.47
     উৎস
    0.47
     Бүген
    0.47
     предупре
    0.47
     гипсо
    0.47
    POSITIVE LOGITS
    امت
    0.48
    しくは
    0.47
    陝
    0.47
    مر
    0.44
    ورٹی
    0.43
    اص
    0.43
    ظ
    0.43
    आप
    0.42
    اتب
    0.42
    तील
    0.41
    Activations Density 0.001%

    No Known Activations