© 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. 171996
    Prev
    Next
    INDEX
    Explanations

    maintenance settings, tourism, POS system, lower insurance, regulations

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

    **introduction and welcome**

    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
     sā
    0.52
     kasutada
    0.52
     использовать
    0.50
    マップ
    0.49
     alimentação
    0.49
     개선
    0.49
     memulai
    0.49
     Saat
    0.48
     محاسبه
    0.48
    獻
    0.48
    POSITIVE LOGITS
    Basically
    0.51
    jg
    0.51
    lni
    0.50
    contr
    0.50
    mr
    0.50
    la
    0.49
    Overall
    0.48
    lg
    0.48
    *****/
    0.47
    Several
    0.47
    Activations Density 0.000%

    No Known Activations