© 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. 41502
    Prev
    Next
    INDEX
    Explanations

    make real

    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
    摀
    -1.86
     Ciebie
    -1.84
    玊
    -1.84
     ſte
    -1.81
    
    -1.77
     ก็
    -1.75
     zoude
    -1.74
    平时
    -1.74
     więc
    -1.72
     overt
    -1.71
    POSITIVE LOGITS
     This
    1.84
     allow
    1.78
    {
    1.73
     They
    1.64
     Those
    1.63
     any
    1.63
     arguably
    1.63
     create
    1.61
     Since
    1.59
    (
    1.55
    Activations Density 0.020%

    No Known Activations