© 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. 34863
    Prev
    Next
    INDEX
    Explanations

    renew

    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
     weiterhin
    -0.97
    做什么
    -0.96
     embora
    -0.94
     recibir
    -0.93
    完成了
    -0.92
     jederzeit
    -0.91
     conveys
    -0.91
     wobei
    -0.91
    עת
    -0.90
     continúa
    -0.90
    POSITIVE LOGITS
    Renew
    1.55
     renew
    1.28
     vigour
    1.27
    renew
    1.24
     renewal
    1.23
     vigor
    1.23
     renewing
    1.20
     acquaintances
    1.16
     Renew
    1.15
     renewed
    1.14
    Activations Density 0.013%

    No Known Activations