© 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. 115723
    Prev
    Next
    INDEX
    Explanations

    current time/location

    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
    Recently
    -0.90
    ngilizce
    -0.84
     گرفته
    -0.82
    bedrijf
    -0.81
     رسد
    -0.81
     entrare
    -0.80
    cé
    -0.79
    sterone
    -0.79
     Recently
    -0.79
    stappen
    -0.78
    POSITIVE LOGITS
     today
    3.42
     present
    3.41
     heutigen
    2.81
    today
    2.73
    現在の
    2.70
     nyky
    2.61
     todays
    2.56
     dagens
    2.48
     нынеш
    2.41
    Present
    2.39
    Activations Density 0.195%

    No Known Activations