© 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. 113891
    Prev
    Next
    INDEX
    Explanations

    if you

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

    declaration

    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
    店家
    0.50
    （
    0.49
    旸
    0.48
    为了
    0.48
    厉害
    0.48
    无奈
    0.48
    同时
    0.48
    新闻
    0.47
    可爱
    0.46
    过
    0.46
    POSITIVE LOGITS
     wäre
    0.47
     conceivably
    0.46
     menyampaikan
    0.45
     awaiting
    0.44
     apresentar
    0.44
    män
    0.43
     potrebbe
    0.41
    諜
    0.41
     istri
    0.41
     sä
    0.40
    Activations Density 0.000%

    No Known Activations