© 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. 10-GEMMASCOPE-RES-131K
    7. 20368
    Prev
    Next
    INDEX
    Explanations

    today

    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_10/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
    6
    -1.55
     without
    -1.35
     another
    -1.33
     a
    -1.33
    鋮
    -1.32
    some
    -1.31
    7
    -1.31
    one
    -1.28
    3
    -1.28
     sebagai
    -1.27
    POSITIVE LOGITS
     obecnie
    1.59
     actualmente
    1.55
     today
    1.51
     현재
    1.50
     любого
    1.41
    当前
    1.37
     dzisiaj
    1.28
     такие
    1.26
     currently
    1.24
     сьогодні
    1.21
    Activations Density 0.085%

    No Known Activations