© 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. 47074
    Prev
    Next
    INDEX
    Explanations

    over

    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
     AIS
    -0.75
     تری
    -0.71
    ļi
    -0.71
    kiet
    -0.69
     Christus
    -0.69
     artikkelen
    -0.69
    cea
    -0.68
    ɫ
    -0.68
    kloped
    -0.68
    Mó
    -0.68
    POSITIVE LOGITS
     over
    4.72
    Over
    3.30
    over
    3.02
     Over
    3.00
     OVER
    2.86
    OVER
    2.48
     över
    2.41
     над
    2.16
    tover
    1.84
     ponad
    1.84
    Activations Density 0.030%

    No Known Activations