© 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. 127320
    Prev
    Next
    INDEX
    Explanations

    global variables and scope

    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
    他自己
    -2.70
    ཋ
    -2.69
     человек
    -2.42
    ㈰
    -2.39
    欸
    -2.36
    さん
    -2.34
    ஂ
    -2.34
    神
    -2.33
    퐹
    -2.31
    ᾥ
    -2.25
    POSITIVE LOGITS
         
    3.17
            
    3.11
        
    3.09
     Allgemeinen
    2.58
     Notably
    2.58
    躋
    2.52
     Primarily
    2.52
    ?”
    2.48
       
    2.47
    但我
    2.47
    Activations Density 0.001%

    No Known Activations