© 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. 81545
    Prev
    Next
    INDEX
    Explanations

    state of completion or arrival

    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
     immediately
    -1.74
     now
    -1.70
     soon
    -1.52
    immediately
    -1.46
     once
    -1.45
     quickly
    -1.43
     сразу
    -1.41
     today
    -1.41
     while
    -1.41
     before
    -1.41
    POSITIVE LOGITS
     allá
    1.02
     czyli
    0.99
     xong
    0.98
     級
    0.97
    鉝
    0.94
    ٨
    0.93
     என்ப
    0.93
     katastro
    0.90
     bezw
    0.90
    świ
    0.89
    Activations Density 0.090%

    No Known Activations