© 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. 34-GEMMASCOPE-RES-131K
    7. 32376
    Prev
    Next
    INDEX
    Explanations

    pay and union negotiations

    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
    メモリ
    -0.88
     nonprofits
    -0.79
     Republican
    -0.79
     hijas
    -0.78
    (""
    -0.76
     Literatur
    -0.76
     SB
    -0.76
     компьютера
    -0.75
     criaturas
    -0.75
    favourites
    -0.74
    POSITIVE LOGITS
     ballot
    1.05
     pay
    0.94
     ballots
    0.92
     ballo
    0.91
     Ballot
    0.88
    तीय
    0.79
     employers
    0.78
     employer
    0.77
     nego
    0.76
     Ballo
    0.75
    Activations Density 0.011%

    No Known Activations