© 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. 90581
    Prev
    Next
    INDEX
    Explanations

    discrepancy between values

    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
    ни
    -2.95
    錵
    -2.77
    灕
    -2.75
     сына
    -2.67
    蜑
    -2.63
    0
    -2.61
    
    -2.53
    ྅
    -2.50
     hilfre
    -2.48
    鄜
    -2.48
    POSITIVE LOGITS
    e
    2.69
     “
    2.09
    </sub>
    2.06
     It
    2.05
     After
    2.02
    p
    2.00
    合わせた
    1.97
    l
    1.94
    ряду
    1.92
     There
    1.91
    Activations Density 0.003%

    No Known Activations