© 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. 22-GEMMASCOPE-RES-131K
    7. 64388
    Prev
    Next
    INDEX
    Explanations

    to be different

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ologi
    -0.88
    损
    -0.87
     reliability
    -0.85
     ESTIM
    -0.85
     consistent
    -0.82
    consistent
    -0.81
    ולים
    -0.77
     compositeur
    -0.77
    یرات
    -0.77
    欢乐
    -0.77
    POSITIVE LOGITS
     boring
    1.58
     bored
    1.52
     boredom
    1.38
    bored
    1.27
     monotony
    1.25
    boring
    1.20
    Boring
    1.19
     uninteresting
    1.19
     bland
    1.12
     Boring
    1.09
    Activations Density 0.072%

    No Known Activations