© 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. 127429
    Prev
    Next
    INDEX
    Explanations

    I was / I have

    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
     is
    -2.28
     แต่
    -1.84
    但是
    -1.82
     但是
    -1.75
     then
    -1.72
     But
    -1.69
     to
    -1.59
     اما
    -1.58
    着一
    -1.52
    -
    -1.52
    POSITIVE LOGITS
     parfait
    1.60
     impreso
    1.48
    __('
    1.48
     lloc
    1.45
     februari
    1.44
     jScrollPane
    1.41
     >(
    1.39
    所の
    1.38
    的变化
    1.38
     !...
    1.37
    Activations Density 0.051%

    No Known Activations