© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79477
    Prev
    Next
    INDEX
    Explanations

    all over or across

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     الده
    -0.89
    ⇈
    -0.83
    목
    -0.75
     Overlay
    -0.75
    Overlap
    -0.75
    的是
    -0.74
    Overlay
    -0.74
     国際
    -0.71
     mediante
    -0.71
    𝙩
    -0.71
    POSITIVE LOGITS
     over
    5.69
    over
    2.77
     över
    2.55
    Over
    2.30
     над
    2.05
     OVER
    2.03
     Over
    1.95
     across
    1.88
     sobre
    1.80
     über
    1.73
    Activations Density 0.018%

    No Known Activations