© 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. 11975
    Prev
    Next
    INDEX
    Explanations

    words starting with "Pos"

    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
    觏
    -2.69
     δύο
    -2.69
    ON
    -2.64
    饹
    -2.55
    潆
    -2.55
    快要
    -2.50
    л
    -2.48
    ではでは
    -2.39
    不该
    -2.36
    
    -2.36
    POSITIVE LOGITS
    ⢌
    2.25
     теми
    2.19
    鼉
    2.09
    抟
    2.08
     явно
    2.05
     twitch
    2.03
    ו
    2.02
     Россия
    2.00
    ッチン
    1.96
    咝
    1.96
    Activations Density 0.006%

    No Known Activations