© 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. 23467
    Prev
    Next
    INDEX
    Explanations

    account for proportions

    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
    soort
    -0.79
     dared
    -0.76
    Халы
    -0.75
    鄴
    -0.72
    скільки
    -0.70
    جيل
    -0.70
     Dunham
    -0.70
    ofer
    -0.70
    pagnol
    -0.69
    惘
    -0.69
    POSITIVE LOGITS
     accounted
    2.94
     constitute
    2.91
     accounting
    2.88
     account
    2.80
     comprise
    2.73
     accounts
    2.70
     chiếm
    2.67
     constitutes
    2.66
     comprises
    2.55
     constituted
    2.53
    Activations Density 0.188%

    No Known Activations