© 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. 35617
    Prev
    Next
    INDEX
    Explanations

    programming syntax

    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
     savons
    -1.13
    Exited
    -1.08
    دانلود
    -1.06
    多肉
    -1.06
    行事
    -1.03
    それにしても
    -1.02
     fucker
    -1.02
     pernic
    -1.01
    や
    -0.99
    穫
    -0.99
    POSITIVE LOGITS
     достижения
    0.95
     obok
    0.92
    Tra
    0.89
     tilgjenge
    0.89
     give
    0.88
     controladores
    0.87
    為に
    0.86
    multicolumn
    0.85
     vendido
    0.85
     leased
    0.84
    Activations Density 0.001%

    No Known Activations