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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13665
    Prev
    Next
    INDEX
    Explanations

    interact with

    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
    姈
    -2.78
    厹
    -2.44
    
    -2.42
    行って
    -2.38
     puramente
    -2.34
    氿
    -2.33
     relativamente
    -2.30
     ubiquitous
    -2.27
     farther
    -2.23
    퐿
    -2.22
    POSITIVE LOGITS
    
    2.78
     passés
    2.52
     kimdir
    2.48
    تیجه
    2.33
     sedih
    2.27
     There
    2.23
    ﹶ
    2.22
     個室
    2.22
    ,  
    2.20
     wunderbar
    2.17
    Activations Density 0.003%

    No Known Activations