© 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. 149796
    Prev
    Next
    INDEX
    Explanations

    master of skills and titles

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

    master switches, plan, degree, thesis

    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
    Not in Any Lists

    No Comments

    Negative Logits
     тра
    0.64
     воен
    0.57
     odors
    0.54
     а
    0.50
    благо
    0.50
     dàng
    0.50
     exhausts
    0.49
    緬
    0.49
     desafíos
    0.48
     وړ
    0.47
    POSITIVE LOGITS
     Master
    1.16
     master
    1.12
     MASTER
    1.08
    master
    1.04
     Masters
    0.99
     masters
    0.95
    Master
    0.95
    マスター
    0.83
    MASTER
    0.82
     マスター
    0.82
    Activations Density 0.042%

    No Known Activations