© 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. 130183
    Prev
    Next
    INDEX
    Explanations

    closing delimiters

    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
    _
    -2.02
     After
    -1.91
     or
    -1.90
     During
    -1.81
    <td>
    -1.79
     would
    -1.71
     t
    -1.69
     usually
    -1.68
     will
    -1.67
     reasonably
    -1.67
    POSITIVE LOGITS
    琑
    2.25
    缯
    2.22
    
    2.19
    鬭
    2.16
     také
    2.14
    鹩
    2.11
     varier
    2.11
    end
    2.09
    罍
    2.09
    新た
    2.05
    Activations Density 0.013%

    No Known Activations