© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33513
    Prev
    Next
    INDEX
    Explanations

    Chief X officer, ONE time units

    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
    Not in Any Lists

    No Comments

    Negative Logits
     geene
    -1.73
     män
    -1.60
     blusa
    -1.58
     perpé
    -1.55
     kän
    -1.53
     läs
    -1.50
     tunik
    -1.47
     ſou
    -1.46
     bensin
    -1.45
     hunne
    -1.41
    POSITIVE LOGITS
    p
    1.62
     to
    1.62
     if
    1.57
    n
    1.57
     as
    1.46
    u
    1.41
     it
    1.39
    ;
    1.39
     in
    1.39
    o
    1.38
    Activations Density 0.003%

    No Known Activations