© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38718
    Prev
    Next
    INDEX
    Explanations

    medical citations

    np_acts-logits-general · gemini-2.5-flash-lite

    year numbers (2014, 2015, 2016, etc.) in web content, articles, and technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Not in Any Lists

    No Comments

    Negative Logits
      
    -1.35
    ↵↵
    -1.34
     for
    -1.27
     began
    -1.23
     but
    -1.20
     more
    -1.20
     is
    -1.19
    That
    -1.16
     on
    -1.14
     has
    -1.12
    POSITIVE LOGITS
     parut
    2.19
     frança
    1.80
     multicolore
    1.71
     fuis
    1.70
     indiví
    1.64
     neutre
    1.58
     convain
    1.57
     manquante
    1.56
     sandalias
    1.55
     dezelve
    1.55
    Activations Density 0.001%

    No Known Activations