© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27324
    Prev
    Next
    INDEX
    Explanations

    money spent or reinvested

    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
    uransi
    -1.03
    lında
    -0.95
    ข้อมูล
    -0.91
    Стоимость
    -0.90
    Financi
    -0.90
    Мини
    -0.89
    Projected
    -0.88
    堑
    -0.88
    MongoClient
    -0.88
    jungan
    -0.86
    POSITIVE LOGITS
    :{
    1.17
     it
    1.13
     used
    1.12
     recipients
    1.07
     money
    1.04
     Gläub
    1.02
    了不少
    1.00
     kullanılır
    0.99
     głównie
    0.96
     distribution
    0.94
    Activations Density 0.053%

    No Known Activations