© 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. 20241
    Prev
    Next
    INDEX
    Explanations

    names like Kari, Ava, and Michele

    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
    -
    -2.83
     to
    -2.78
     bemerkt
    -2.69
    髏
    -2.56
    蜘
    -2.42
     适合
    -2.42
     beobachtet
    -2.39
    攫
    -2.31
     主要
    -2.31
     allegedly
    -2.31
    POSITIVE LOGITS
    ⢓
    2.88
    鎹
    2.45
    哟
    2.34
    ised
    2.33
    
    2.31
    after
    2.30
     sebag
    2.28
    ians
    2.27
     SEÑ
    2.23
    Ꮞ
    2.22
    Activations Density 0.013%

    No Known Activations