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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1042
    Prev
    Next
    INDEX
    Explanations

    judge or judicial titles

    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_10/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
    d
    -1.86
    y
    -1.72
    z
    -1.63
     in
    -1.63
    en
    -1.63
     During
    -1.63
     on
    -1.59
    re
    -1.56
    ne
    -1.53
    n
    -1.53
    POSITIVE LOGITS
     überprüft
    2.03
    髏
    1.91
    都已经
    1.80
     ganzes
    1.79
     solches
    1.71
    .
    1.70
     ранее
    1.68
     utilisateurs
    1.67
     dispuestos
    1.66
     wes
    1.61
    Activations Density 0.003%

    No Known Activations