© 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. 92396
    Prev
    Next
    INDEX
    Explanations

    completing place names and titles

    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
    Catholic
    -1.20
     Catholic
    -1.20
     Catholics
    -0.97
    OUTPUT
    -0.81
    Club
    -0.81
     católica
    -0.80
     organizaciones
    -0.80
     catholique
    -0.79
    Посилання
    -0.79
     catholic
    -0.78
    POSITIVE LOGITS
    Province
    0.93
    Expire
    0.90
     frère
    0.88
    expire
    0.88
    contexts
    0.86
    provin
    0.85
    Superior
    0.85
    IconModule
    0.84
     Province
    0.83
     provincial
    0.79
    Activations Density 0.013%

    No Known Activations