© 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. 229546
    Prev
    Next
    INDEX
    Explanations

    appeal, subjected, frustrated

    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
     Sı
    0.45
     halved
    0.44
     نہایت
    0.44
    实行
    0.44
    etum
    0.44
     polyclonal
    0.44
    髄
    0.43
     Verz
    0.43
     Định
    0.43
     vehemently
    0.43
    POSITIVE LOGITS
    логі
    0.54
    cig
    0.45
    空間
    0.44
     但是
    0.43
     BUT
    0.43
    נע
    0.43
    吼
    0.43
    但是
    0.43
    StdHandle
    0.43
     اړ
    0.43
    Activations Density 0.002%

    No Known Activations