© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82398
    Prev
    Next
    INDEX
    Explanations

    devices and machines

    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
     LED
    -0.90
     inmediatamente
    -0.90
     opty
    -0.83
     falar
    -0.80
     Auß
    -0.79
     pixel
    -0.77
    白天
    -0.77
    洋服
    -0.75
     ah
    -0.75
     продуктов
    -0.75
    POSITIVE LOGITS
    antMatchers
    1.09
    歟
    1.08
     geforce
    1.07
     artig
    1.03
    EOUS
    1.01
     joan
    1.00
     recipiente
    0.99
     kalender
    0.98
    UFC
    0.98
    "،
    0.97
    Activations Density 0.468%

    No Known Activations