© 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. 72865
    Prev
    Next
    INDEX
    Explanations

    arrival of independence

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

    Alert Design

    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
     trest
    0.52
     mechanical
    0.48
     win
    0.47
     triad
    0.46
     guter
    0.44
     system
    0.44
     \&
    0.44
     tus
    0.43
     yellows
    0.42
     bench
    0.42
    POSITIVE LOGITS
    ﹍
    0.51
     sırasında
    0.47
    。“
    0.47
    ！（
    0.46
    出错
    0.46
    传播
    0.45
    激发
    0.45
    出现了
    0.45
    .'%
    0.45
    股权
    0.44
    Activations Density 0.000%

    No Known Activations