© 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. 751
    Prev
    Next
    INDEX
    Explanations

    Rie, Benton, Bedford, Pratt

    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
    ly
    -3.22
    the
    -3.03
    ꯶
    -2.83
    m
    -2.83
    你的
    -2.61
    ו
    -2.58
    坶
    -2.38
     возможность
    -2.36
     Direktor
    -2.25
    躂
    -2.25
    POSITIVE LOGITS
    しますが
    2.95
    偌
    2.28
     婚礼
    2.25
    常用的
    2.22
    糨
    2.20
    箩
    2.20
    
    2.14
    薮
    2.11
     But
    2.09
     entendi
    2.09
    Activations Density 0.012%

    No Known Activations