© 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. 2528
    Prev
    Next
    INDEX
    Explanations

    interest rates and APR

    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
    lamento
    -0.82
    ītā
    -0.79
    £
    -0.76
    readValue
    -0.75
    احب
    -0.75
    MediaType
    -0.73
    гр
    -0.73
    clientWidth
    -0.73
     Vorschriften
    -0.73
     £
    -0.73
    POSITIVE LOGITS
     interest
    1.73
     rate
    1.53
     interés
    1.30
     Interest
    1.27
    interest
    1.26
    利率
    1.23
    Interest
    1.19
     rates
    1.17
     Rate
    1.13
    率
    1.11
    Activations Density 0.013%

    No Known Activations