© 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. 34-GEMMASCOPE-RES-131K
    7. 109534
    Prev
    Next
    INDEX
    Explanations

    Of counsel / attorney roles

    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_34/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
    iname
    -0.80
     creer
    -0.79
    是因为
    -0.71
    ナチュラル
    -0.70
     寝
    -0.68
     medicina
    -0.67
     днев
    -0.67
     atrium
    -0.67
    estand
    -0.66
     resc
    -0.66
    POSITIVE LOGITS
     counsel
    4.63
     Counsel
    3.97
    Counsel
    3.67
     COUNSEL
    2.73
    coun
    2.63
     counsels
    2.36
     legal
    1.73
    COUN
    1.64
     coun
    1.55
     Coun
    1.50
    Activations Density 0.118%

    No Known Activations