© 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. 22-GEMMASCOPE-RES-131K
    7. 104367
    Prev
    Next
    INDEX
    Explanations

    function arguments and parameters

    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_22/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
    EmailAddress
    -0.98
     są
    -0.86
    íí
    -0.84
     estaban
    -0.84
     элемент
    -0.83
     моего
    -0.82
    beo
    -0.81
     où
    -0.81
     ziem
    -0.81
     моей
    -0.80
    POSITIVE LOGITS
     voluto
    1.02
    meanor
    0.91
    ၟ
    0.90
    vatel
    0.90
     may
    0.90
    Kommun
    0.88
     complexity
    0.88
     substantial
    0.87
    dillera
    0.87
    ybė
    0.86
    Activations Density 0.022%

    No Known Activations