© 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. 10-GEMMASCOPE-RES-131K
    7. 87348
    Prev
    Next
    INDEX
    Explanations

    AM/PM time indicators

    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_10/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
    因為
    -1.81
     zvuky
    -1.80
     hlavy
    -1.76
    нями
    -1.73
    可以
    -1.67
     Aufmerksamkeit
    -1.66
     Empfindung
    -1.64
     erwähnten
    -1.63
     neuem
    -1.63
     demselben
    -1.62
    POSITIVE LOGITS
    :
    2.20
     about
    1.84
     "
    1.78
    ."
    1.77
    ’
    1.71
    ↵
    1.66
     has
    1.58
     with
    1.57
     fairly
    1.55
     in
    1.52
    Activations Density 0.071%

    No Known Activations