© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61167
    Prev
    Next
    INDEX
    Explanations

    find what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     рассказал
    0.44
     удалось
    0.43
    遭遇
    0.41
    renowned
    0.40
     Featuring
    0.40
    founded
    0.39
     Yii
    0.39
    стра
    0.39
     துன்ப
    0.39
    Й
    0.39
    POSITIVE LOGITS
    ida
    0.44
     vragen
    0.44
     ત્રણ
    0.43
     consists
    0.42
     واحدة
    0.42
    ikke
    0.41
     ضرور
    0.41
    姮
    0.41
     यदि
    0.41
    keiten
    0.41
    Activations Density 0.008%

    No Known Activations