© 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. 22-GEMMASCOPE-RES-131K
    7. 71669
    Prev
    Next
    INDEX
    Explanations

    age in years

    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_22/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
     recetas
    -0.97
     April
    -0.97
     inteligentes
    -0.95
     Pets
    -0.92
    agang
    -0.91
     PUSTAKA
    -0.90
    curité
    -0.90
    読
    -0.90
     značky
    -0.89
     October
    -0.89
    POSITIVE LOGITS
    elded
    0.89
    たまに
    0.84
     Svizzera
    0.82
    อิง
    0.80
    不錯
    0.79
    了一個
    0.77
    食べ物
    0.77
    値段
    0.75
    esterno
    0.75
    Karla
    0.74
    Activations Density 0.003%

    No Known Activations