© 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. 40-GEMMASCOPE-2-RES-262K
    7. 169838
    Prev
    Next
    INDEX
    Explanations

    pastoral care and advisors

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     school
    0.70
     sekolah
    0.67
     шко
    0.65
    école
    0.64
    学校
    0.61
    school
    0.61
     schools
    0.59
     escola
    0.59
    校
    0.59
    Schools
    0.59
    POSITIVE LOGITS
     shepherds
    0.50
     advisors
    0.49
     Pastoral
    0.48
     advisers
    0.47
     Counselling
    0.47
     counselling
    0.46
     hom
    0.46
     roommates
    0.45
     pastoral
    0.45
     House
    0.44
    Activations Density 0.002%

    No Known Activations