© 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. 22-GEMMASCOPE-RES-131K
    4. 71272
    Prev
    Next
    INDEX
    Explanations

    left behind

    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_22/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
     use
    -1.73
     or
    -1.72
     for
    -1.72
     by
    -1.60
     if
    -1.56
     when
    -1.54
     an
    -1.52
     methods
    -1.49
     it
    -1.49
     using
    -1.46
    POSITIVE LOGITS
     AMAZING
    1.41
    んでる
    1.41
     vendredi
    1.39
     jeudi
    1.38
     ܐ
    1.29
     ܕ
    1.28
     funktioner
    1.27
     evtl
    1.26
     errone
    1.25
    мання
    1.24
    Activations Density 0.000%

    No Known Activations