© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9987
    Prev
    Next
    INDEX
    Explanations

    manufacturing terms

    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
    ":"+
    -1.30
     kovo
    -1.29
    無論
    -1.27
    (!__
    -1.27
    
    -1.26
    símbolo
    -1.25
    になりますが
    -1.24
     they
    -1.22
     obiettivi
    -1.21
    不觉
    -1.17
    POSITIVE LOGITS
     कैसे
    1.34
    喜欢的
    1.23
    ÈRE
    1.13
    ”?
    1.13
    ):
    1.12
      
    1.07
    ŚĆ
    1.06
               
    1.05
    机器人
    1.04
     Decke
    1.04
    Activations Density 0.117%

    No Known Activations