© 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. 211920
    Prev
    Next
    INDEX
    Explanations

    leading declaration of grandeur

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

    technical terms and code delimiters

    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
     społecz
    0.50
     思う
    0.48
     Sunday
    0.47
     ツ
    0.46
    RNN
    0.45
    Ｒ
    0.45
    нические
    0.45
     vandal
    0.44
    ill
    0.44
     歴史
    0.44
    POSITIVE LOGITS
    拔
    0.53
    )});
    0.46
     Traction
    0.45
    եղ
    0.45
     antibiot
    0.45
    >());
    0.45
    >(){
    0.45
     reutil
    0.45
     stessi
    0.44
    茦
    0.44
    Activations Density 0.000%

    No Known Activations