© 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. 118529
    Prev
    Next
    INDEX
    Explanations

    Roman Catholic figures and institutions

    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
     Lutheran
    -0.97
    Outlined
    -0.80
    ようですが
    -0.76
    了个
    -0.74
     неодно
    -0.73
    χ
    -0.70
    静静
    -0.70
     Charities
    -0.69
     Reactive
    -0.68
    scanf
    -0.67
    POSITIVE LOGITS
    Catholic
    0.96
    Tablet
    0.88
     tablet
    0.84
     Catholic
    0.83
    endenza
    0.82
    tablet
    0.81
    WY
    0.80
     popolari
    0.77
     Soccerway
    0.77
     Tablet
    0.76
    Activations Density 0.032%

    No Known Activations