© 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-262K
    7. 46042
    Prev
    Next
    INDEX
    Explanations

    names and teachers

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    elfalt
    0.44
     culto
    0.43
    œuf
    0.40
    有着
    0.40
    wna
    0.39
     Allianz
    0.39
     stijl
    0.39
     liés
    0.39
     दट
    0.38
    ̶
    0.38
    POSITIVE LOGITS
     teacher
    0.59
     учитель
    0.54
     teachers
    0.53
     Teacher
    0.53
    Teacher
    0.53
    Answer
    0.52
     Answer
    0.51
     শিক্ষক
    0.51
    Teachers
    0.50
     Classroom
    0.48
    Activations Density 0.002%

    No Known Activations