© 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. 32903
    Prev
    Next
    INDEX
    Explanations

    continuous and following word

    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
    继续
    -1.23
     continuing
    -1.16
     continue
    -1.14
     продолжа
    -1.13
    continuing
    -1.10
     continuation
    -1.02
    繼續
    -1.02
     sourire
    -0.99
     ادامه
    -0.98
     piattaforma
    -0.97
    POSITIVE LOGITS
    不断的
    1.48
     Continuous
    1.37
    Continuous
    1.25
    continuous
    1.23
     непре
    1.17
     continuous
    1.16
    ），
    1.13
    ”，
    1.13
     Contin
    1.05
    ously
    1.03
    Activations Density 0.030%

    No Known Activations