© 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. 109552
    Prev
    Next
    INDEX
    Explanations

    age groups

    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
     students
    -0.90
    施行
    -0.84
    vish
    -0.79
     bajo
    -0.74
    lós
    -0.72
    oluciones
    -0.71
     children
    -0.70
     ask
    -0.69
     Block
    -0.69
     ferr
    -0.68
    POSITIVE LOGITS
     age
    1.63
    Age
    1.36
     возраст
    1.30
     Age
    1.20
     masters
    1.13
     Masters
    1.12
    age
    1.11
    マスター
    1.09
    AGE
    1.08
    年龄
    1.06
    Activations Density 0.013%

    No Known Activations