© 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. 11769
    Prev
    Next
    INDEX
    Explanations

    last or lastly

    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
    ᵑ
    -0.73
    SDK
    -0.72
    gon
    -0.72
    ITA
    -0.71
    υν
    -0.71
    arkas
    -0.71
    previous
    -0.69
    ProgressBar
    -0.69
    azzi
    -0.67
    끔
    -0.67
    POSITIVE LOGITS
    最后
    2.98
    最後に
    2.95
     last
    2.86
     lastly
    2.67
    最後
    2.50
     zuletzt
    2.41
    Lastly
    2.39
     Lastly
    2.28
     最后
    2.14
     terakhir
    1.93
    Activations Density 0.035%

    No Known Activations