© 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. 22-GEMMASCOPE-RES-131K
    7. 71539
    Prev
    Next
    INDEX
    Explanations

    now, immediately, present moment

    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_22/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
    춰
    -0.89
     upstairs
    -0.85
    дає
    -0.83
    glue
    -0.82
    ayashi
    -0.82
    riente
    -0.82
     finalmente
    -0.81
    に出て
    -0.81
     étape
    -0.81
     experiência
    -0.80
    POSITIVE LOGITS
     now
    1.66
     теперь
    1.09
     sparked
    0.96
    Теперь
    0.95
     adesso
    0.91
     agora
    0.90
    beforeAll
    0.90
    ল
    0.88
    開始
    0.87
     immediately
    0.86
    Activations Density 0.030%

    No Known Activations