© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15353
    Prev
    Next
    INDEX
    Explanations

    ellipse cx and cy attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     हेक्टेयर
    1.03
     imassa
    1.02
     douleurs
    1.02
     idha
    0.99
     errMsg
    0.99
     semillas
    0.96
     estabelecer
    0.95
    СФ
    0.95
     principales
    0.94
    谥
    0.94
    POSITIVE LOGITS
    ปก
    0.70
    rica
    0.70
     money
    0.68
    ท้าย
    0.67
    He
    0.67
    カラー
    0.67
    keley
    0.66
    /
    0.66
     Whitney
    0.66
    dad
    0.65
    Activations Density 0.001%

    No Known Activations