© 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. 75998
    Prev
    Next
    INDEX
    Explanations

    celebrations and events

    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
     Beres
    -0.80
    žev
    -0.77
    檎
    -0.75
    pmd
    -0.73
    างเกง
    -0.72
    ゴリー
    -0.71
    rangle
    -0.70
     macrophages
    -0.70
    ynek
    -0.69
    めていた
    -0.69
    POSITIVE LOGITS
     wedding
    4.34
     weddings
    3.42
     Wedding
    2.92
    wedding
    2.89
     birthday
    2.84
     graduation
    2.73
     funeral
    2.69
    Wedding
    2.66
     marriage
    2.53
     Weddings
    2.33
    Activations Density 0.055%

    No Known Activations