© 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. 71128
    Prev
    Next
    INDEX
    Explanations

    transformed a, physician can, society journal

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

    action signing change

    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
    老師
    0.45
    引用
    0.43
    遥
    0.41
    δει
    0.39
     zeigt
    0.39
    老师
    0.39
    鈐
    0.38
     ಗೊತ್ತ
    0.38
     स्ट्रीम
    0.38
    霍
    0.38
    POSITIVE LOGITS
    𝚗
    0.48
    <unused169>
    0.45
    heira
    0.45
    ophobia
    0.45
    omely
    0.44
     තුළ
    0.44
     канце
    0.44
     Virtually
    0.44
     empêcher
    0.44
     необходимости
    0.44
    Activations Density 0.002%

    No Known Activations