© 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. 38037
    Prev
    Next
    INDEX
    Explanations

    XML configuration and blog posts

    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
    censo
    -0.78
    ordenadas
    -0.77
     солнца
    -0.77
     premises
    -0.77
    pronounced
    -0.76
     сім
    -0.76
     làng
    -0.75
     much
    -0.75
    女主
    -0.75
    niejsza
    -0.74
    POSITIVE LOGITS
    NewLabel
    0.94
    zył
    0.91
    ariConfig
    0.90
    ˂
    0.88
    Carthy
    0.87
    .$
    0.85
    losa
    0.85
    .!
    0.85
    ってもら
    0.85
    Namara
    0.84
    Activations Density 0.186%

    No Known Activations