© 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. 54238
    Prev
    Next
    INDEX
    Explanations

    early/young age

    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
    paikan
    -0.81
    畢
    -0.79
     special
    -0.77
    റ
    -0.77
     bebés
    -0.76
     спеціаль
    -0.76
    ütten
    -0.76
     久
    -0.75
     ร์
    -0.75
    特
    -0.74
    POSITIVE LOGITS
     age
    2.00
    age
    1.37
     edad
    1.35
     idade
    1.23
     età
    1.01
     usia
    0.99
     ages
    0.95
    AGE
    0.91
     âge
    0.86
    Age
    0.82
    Activations Density 0.011%

    No Known Activations