© 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. 52726
    Prev
    Next
    INDEX
    Explanations

    school and official greetings

    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
     exquisitely
    0.38
     minimalistic
    0.38
     extraordinary
    0.37
     consuming
    0.37
     idealized
    0.37
    的事
    0.36
     certes
    0.36
     characteristic
    0.36
     /ˈ
    0.35
     WTF
    0.35
    POSITIVE LOGITS
     جديد
    0.42
     alunos
    0.42
     ق
    0.41
     भेदभाव
    0.39
     alumnos
    0.38
     vecchio
    0.38
     يقول
    0.38
     केसा
    0.38
     이라고
    0.38
     prostit
    0.37
    Activations Density 0.012%

    No Known Activations