© 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. 87337
    Prev
    Next
    INDEX
    Explanations

    alert and alerta components

    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
     ‘
    -2.05
     ’
    -1.48
     które
    -1.48
     แต่
    -1.45
        
    -1.44
     zarówno
    -1.44
     delightful
    -1.43
    …”
    -1.39
     sublime
    -1.39
     singularly
    -1.38
    POSITIVE LOGITS
     there
    2.13
     Sénat
    1.59
    鏵
    1.57
     tarts
    1.56
     kere
    1.52
    夲
    1.49
     Diman
    1.48
     lagos
    1.48
    ♻
    1.48
    癡
    1.47
    Activations Density 0.002%

    No Known Activations