© 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. 19749
    Prev
    Next
    INDEX
    Explanations

    leverage to advantage

    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
    ни
    -2.86
     This
    -2.59
    ꜆
    -2.58
    9
    -2.58
     forwarded
    -2.56
    I
    -2.48
    猻
    -2.41
    琑
    -2.39
     allgemeine
    -2.38
     rapida
    -2.36
    POSITIVE LOGITS
    潆
    2.73
    CONSIN
    2.55
    寕
    2.50
    
    2.39
     TAMBIÉN
    2.34
     him
    2.22
    Ꮨ
    2.19
    姽
    2.19
    ᠁
    2.16
    ‪.‬‬
    2.14
    Activations Density 0.003%

    No Known Activations