© 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. 34592
    Prev
    Next
    INDEX
    Explanations

    with which

    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
     использова
    -1.13
     использовать
    -0.93
     использу
    -0.88
    붙
    -0.88
     by
    -0.85
    seen
    -0.83
    deliver
    -0.82
    used
    -0.81
    gave
    -0.79
    held
    -0.79
    POSITIVE LOGITS
    武装
    1.23
    burden
    1.09
     пользоваться
    1.04
     versehen
    1.03
     воспользова
    1.00
     greeted
    0.95
     пользу
    0.91
     занимается
    0.90
     burdened
    0.89
     определяется
    0.88
    Activations Density 0.010%

    No Known Activations