© 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. 34-GEMMASCOPE-RES-131K
    7. 59916
    Prev
    Next
    INDEX
    Explanations

    file names and types

    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_34/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
     chỉ
    -0.79
    ۲۲
    -0.72
     alberi
    -0.70
    цима
    -0.69
    flame
    -0.68
     Cougar
    -0.68
    akan
    -0.67
     организаций
    -0.67
     autón
    -0.66
     dil
    -0.66
    POSITIVE LOGITS
     Jeremy
    0.80
    lineTo
    0.76
     borehole
    0.75
    悍
    0.75
    HttpGet
    0.72
    httpd
    0.70
    Jeremy
    0.70
     Elena
    0.69
    Elena
    0.69
    BrowserRouter
    0.68
    Activations Density 0.590%

    No Known Activations