© 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. 47928
    Prev
    Next
    INDEX
    Explanations

    Guru Purnima; acharya buddharakkhita

    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
     сни
    -0.82
    tableFuture
    -0.76
    хозяй
    -0.75
    抱
    -0.74
     petitioned
    -0.69
     lembaga
    -0.68
     resizing
    -0.68
     Hanuman
    -0.68
    WISH
    -0.67
    tcl
    -0.67
    POSITIVE LOGITS
     Ina
    0.92
    外国人
    0.87
    浏览器
    0.81
    研发
    0.72
    Ina
    0.71
    ProductList
    0.71
     Dijkstra
    0.71
    Individual
    0.69
    álisis
    0.69
     $_
    0.68
    Activations Density 0.017%

    No Known Activations