© 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. 34472
    Prev
    Next
    INDEX
    Explanations

    eventually

    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
     WebApplication
    -0.90
    idespread
    -0.88
     sterk
    -0.85
     هنگام
    -0.84
    nią
    -0.82
    XXXXXX
    -0.81
    ッキング
    -0.81
     handen
    -0.81
    τών
    -0.81
    opoly
    -0.80
    POSITIVE LOGITS
     eventually
    8.13
    Eventually
    7.00
     Eventually
    6.91
    eventually
    6.63
     eventual
    5.47
     eventualmente
    4.53
     irgendwann
    4.28
     uiteindelijk
    3.78
     ultimately
    3.72
     sooner
    3.36
    Activations Density 0.185%

    No Known Activations