© 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. 12725
    Prev
    Next
    INDEX
    Explanations

    gin cocktails

    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
    
    -2.63
     purpoſe
    -2.56
     juſ
    -2.52
    佾
    -2.52
    they
    -2.52
     projeto
    -2.52
     unſ
    -2.42
     “
    -2.31
    퐸
    -2.28
     dezelve
    -2.27
    POSITIVE LOGITS
    ."
    2.75
     '
    2.31
     stehenden
    2.27
    孖
    2.19
     Despite
    2.17
     gespannt
    2.16
    таки
    2.14
     "
    2.13
     chug
    2.13
    
    2.11
    Activations Density 0.004%

    No Known Activations