© 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. 217988
    Prev
    Next
    INDEX
    Explanations

    forces, modern, Silver, loss, from, on, All, authority

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

    heavy duty topics

    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
    春夏
    0.50
    聚合
    0.49
    퀀
    0.49
    鏻
    0.48
    儲
    0.47
    زم
    0.46
     жаңы
    0.46
    戰爭
    0.46
    效果
    0.45
    캄
    0.44
    POSITIVE LOGITS
    alon
    0.64
    alo
    0.52
     metod
    0.50
    nemen
    0.49
    rok
    0.49
    irteen
    0.48
    ers
    0.48
    és
    0.48
    ard
    0.46
    he
    0.46
    Activations Density 0.000%

    No Known Activations