© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 647
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    所有
    -1.50
     tramite
    -1.35
     erhielten
    -1.33
     nahmen
    -1.33
    新的
    -1.30
    ON
    -1.30
    Poznám
    -1.29
    　『
    -1.28
    这是一
    -1.28
    ONLY
    -1.27
    POSITIVE LOGITS
     todavía
    1.38
    チュウ
    1.34
     Wartung
    1.30
    
    1.27
     매우
    1.27
    咿
    1.23
     píše
    1.20
     anderer
    1.20
     sector
    1.20
     rapidement
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.