© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 203
    Prev
    Next
    INDEX
    Explanations

    proper nouns after numbers or common words

    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
    
    -1.81
     unangemess
    -1.80
    usión
    -1.67
     australiano
    -1.66
     lorsque
    -1.66
     cansado
    -1.58
     الاول
    -1.55
    をはじめ
    -1.55
    品牌的
    -1.55
    ledem
    -1.55
    POSITIVE LOGITS
    !!!!!!
    1.85
    现在
    1.78
    ísticas
    1.68
    chaft
    1.66
    穣
    1.66
    ͆
    1.63
     registró
    1.59
    ización
    1.59
    ্ল
    1.58
     mostró
    1.55
    Activations Density 0.000%

    No Known Activations