© 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. 249878
    Prev
    Next
    INDEX
    Explanations

    power and winning

    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
    Negative Logits
     마
    0.47
     계획
    0.47
     형식
    0.46
     특
    0.45
     약
    0.45
     narrowing
    0.44
    ]，
    0.44
    planning
    0.44
     alters
    0.43
     지원
    0.43
    POSITIVE LOGITS
    Thickness
    0.51
     tabela
    0.50
    WIDTH
    0.50
     dupa
    0.48
    സർ
    0.47
    ٦
    0.46
     deced
    0.46
    ザー
    0.45
     noticia
    0.44
     Lowest
    0.44
    Activations Density 0.000%

    No Known Activations