© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81371
    Prev
    Next
    INDEX
    Explanations

    Goshen County, Q:

    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
    essy
    -0.82
     pande
    -0.75
    ータ
    -0.74
     embed
    -0.72
     withdrawing
    -0.71
     ciudadana
    -0.71
    ötä
    -0.70
     crib
    -0.70
    outons
    -0.70
    quí
    -0.68
    POSITIVE LOGITS
     Bazaar
    0.81
     安装
    0.76
     voice
    0.75
    安装
    0.74
     Amazon
    0.73
    Actors
    0.73
     recommendations
    0.71
    Rental
    0.71
    чила
    0.70
    Search
    0.69
    Activations Density 0.009%

    No Known Activations