© 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. 20017
    Prev
    Next
    INDEX
    Explanations

    javascript jquery document ready syntax

    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
    </sup>
    -3.03
     You
    -2.66
    </h4>
    -2.50
     And
    -2.48
     '
    -2.44
     ("
    -2.42
    providedIn
    -2.38
     That
    -2.28
    信念
    -2.23
     -
    -2.22
    POSITIVE LOGITS
    
    3.13
    褙
    3.13
    鋨
    2.91
    ꜆
    2.84
    猻
    2.81
     évaluation
    2.75
    埽
    2.67
     icône
    2.66
    硨
    2.63
    
    2.58
    Activations Density 0.011%

    No Known Activations