© 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. 75781
    Prev
    Next
    INDEX
    Explanations

    Swift, Android code snippets

    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
     Umbau
    -1.15
    perate
    -1.12
     that
    -1.04
    ofile
    -1.04
    npy
    -1.03
    FontAwesomeIcon
    -1.02
     מים
    -0.98
     either
    -0.96
     Krieges
    -0.94
     ゆう
    -0.93
    POSITIVE LOGITS
     COVID
    1.02
    Corona
    0.87
     androidx
    0.85
    coronavirus
    0.85
     coronavirus
    0.84
     corona
    0.81
     Covid
    0.80
    新型コロナ
    0.78
    Aspect
    0.78
    Бе
    0.77
    Activations Density 0.121%

    No Known Activations