© 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. 60053
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and codes

    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
     апреля
    -0.90
     wieku
    -0.89
    когда
    -0.87
     so
    -0.87
    вость
    -0.87
    оборот
    -0.85
    мне
    -0.84
     usually
    -0.84
     lingü
    -0.83
     футболка
    -0.82
    POSITIVE LOGITS
    很赞
    1.20
     misericordia
    1.04
     siff
    1.03
     Sloveniji
    1.00
     Glä
    1.00
     penna
    0.97
     popol
    0.95
     življen
    0.94
     veder
    0.94
     materie
    0.93
    Activations Density 0.003%

    No Known Activations