© 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. 99634
    Prev
    Next
    INDEX
    Explanations

    programming imports and code elements

    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
    </i>
    -2.39
     fiel
    -2.28
     copi
    -2.27
     curiosa
    -2.23
    －－－－
    -2.22
     बजाय
    -2.16
     早餐
    -2.14
     fà
    -2.13
    结语
    -2.11
    푏
    -2.09
    POSITIVE LOGITS
    8
    2.66
    .
    2.56
    it
    2.47
     ними
    2.42
    ჻
    2.41
     $
    2.22
     }
    2.17
    7
    2.16
    6
    2.14
     unangemess
    2.11
    Activations Density 0.001%

    No Known Activations