© 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. 25024
    Prev
    Next
    INDEX
    Explanations

    concluding items or sequences

    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
     différentes
    -1.52
     diverses
    -1.48
     rè
    -1.34
    mäs
    -1.32
     😊
    -1.30
     lã
    -1.29
    ܧ
    -1.29
     😁
    -1.29
     dê
    -1.29
    踮
    -1.27
    POSITIVE LOGITS
     one
    1.77
     get
    1.62
     take
    1.59
     their
    1.55
     after
    1.53
     two
    1.51
     for
    1.49
     three
    1.46
     After
    1.44
     chose
    1.44
    Activations Density 0.018%

    No Known Activations