© 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. 11833
    Prev
    Next
    INDEX
    Explanations

    'tea makes' or '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
     order
    -0.93
     ORDER
    -0.78
    ORDER
    -0.76
    Order
    -0.75
    ordre
    -0.74
     including
    -0.71
    order
    -0.71
     getOrder
    -0.70
     system
    -0.69
    Ꮩ
    -0.69
    POSITIVE LOGITS
    sortBy
    0.87
     préférable
    0.87
    每个
    0.85
    itel
    0.84
    ุณ
    0.82
    isEmpty
    0.82
     Спо
    0.80
     каждый
    0.79
    Lew
    0.78
    mucha
    0.77
    Activations Density 0.013%

    No Known Activations