© 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. 89816
    Prev
    Next
    INDEX
    Explanations

    scottish history and scottish literature

    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
     villager
    -0.81
    тона
    -0.80
     Deletion
    -0.75
    marca
    -0.75
    Termin
    -0.75
    🍖
    -0.73
    ৩
    -0.72
    isées
    -0.72
    イギリス
    -0.72
    digde
    -0.71
    POSITIVE LOGITS
     Sco
    0.82
     Covenant
    0.79
     elbise
    0.79
    valier
    0.77
     Xcode
    0.74
     Scot
    0.72
    irsty
    0.71
     Scotland
    0.70
     ointment
    0.70
     portátiles
    0.69
    Activations Density 0.029%

    No Known Activations