© 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. 48379
    Prev
    Next
    INDEX
    Explanations

    obsolete, extinct, defunct

    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
    archiwizowane
    -2.78
    ܆
    -2.55
     Dinas
    -2.53
    derdag
    -2.44
    
    -2.42
     eerste
    -2.34
     ་
    -2.31
     originalmente
    -2.31
    莇
    -2.30
    
    -2.28
    POSITIVE LOGITS
    ↵
    3.70
    
    2.53
     Surprisingly
    2.52
    也
    2.44
     Using
    2.33
    ．．．
    2.33
    ？！”
    2.31
     Shortly
    2.28
    ”、“
    2.25
    '
    2.22
    Activations Density 0.003%

    No Known Activations